A microgrid dispatching method and system based on steady-state curve fitting

Abstract

The present invention provides a microgrid scheduling method and system for steady-state curve fitting, comprising: obtaining unique identifiers of all sensors related to electric energy scheduling in a microgrid, and obtaining first detection data of each sensor according to the unique identifier, establishing a mapping set between the detection time of the first detection data of each sensor and the corresponding time series; constructing a steady-state curve of the first detection data of the sensor in each time series according to the mapping set, and performing curve fitting construction through the first detection data and the unique identifier of the sensor; pre-constructing an electric energy scheduling strategy for the steady-state curve of each detection data, and pre-setting a curve update strategy for each steady-state curve of the detection data; obtaining second detection data of each sensor, fitting the first detection data steady-state curve of the corresponding time series according to the detection time, and executing the electric energy scheduling strategy for the first detection data steady-state curve according to the fitting result.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid dispatching, and in particular to a microgrid dispatching method and system for steady-state curve fitting. Background Art

[0002] At present, the traditional microgrid dispatching is still based on the data of related sensors of different power load ends, energy storage ends and power generation ends for dispatching, such as calculating the power consumption according to the power demand of the load end in real time, calculating the power generation of the power generation end and the storage capacity of the energy storage end, etc. In other words, the above-mentioned different types of sensors need to comprehensively monitor the different states of the microgrid in real time, and execute the corresponding microgrid dispatching strategy under certain conditions. However, the above-mentioned method requires uninterrupted real-time monitoring of each type of sensor. When the sensor fails, the corresponding microgrid dispatching strategy may have a large deviation, and the real-time monitoring of all sensors will also increase the overall dispatching energy consumption of the microgrid. It should be noted that the power load end, energy storage end and power generation end of the microgrid can be in a relatively stable state in a stable environment. The sensors in this stable state may not work, or even if the sensors are damaged in this stable state, the dispatching strategy of the microgrid itself should not be affected. Summary of the invention

[0003] One of the inventive objectives of the present invention is to provide a microgrid scheduling method and system for steady-state curve fitting, wherein the method and system obtain all sensor detection data related to power scheduling in a microgrid under a certain time series, and construct a steady-state curve under the corresponding time series based on the acquired sensor detection data, and execute the scheduling strategy of the corresponding microgrid according to the steady-state curve. The steady-state curve of the multi-type sensor data used in the present invention can execute the microgrid steady-state scheduling strategy of the corresponding sensor damage area when the sensor is damaged, thereby reducing or avoiding large errors caused by sensor damage to the microgrid scheduling strategy.

[0004] Another inventive object of the present invention is to provide a microgrid scheduling method and system for steady-state curve fitting. The method and system, when utilizing the steady-state curve under a certain time series, can eliminate the need for activation and real-time detection of all sensors related to power scheduling. Only one detection is required and the steady-state curve of the sensor detection data of the corresponding time series is fitted to call and execute the corresponding microgrid power scheduling strategy. Therefore, the energy consumption of relevant power scheduling sensors within the microgrid can be saved to a certain extent, so that the microgrid itself has a better energy-saving effect.

[0005] Another inventive object of the present invention is to provide a microgrid scheduling method and system for steady-state curve fitting. The method and system also design a dynamic update method for sensor detection data under the corresponding time series. When microgrid-related equipment is added or removed under certain conditions, the steady-state curve of the corresponding microgrid sensor detection data is updated; or when the microgrid obtains all sensor detection data related to power scheduling during actual detection and the difference between the steady-state curve configured previously is large, the steady-state curve is updated. Therefore, the steady-state curve of the present invention has certain flexibility in the microgrid scheduling process.

[0006] In order to achieve at least one of the above-mentioned invention objects, the present invention further provides a microgrid dispatching method for steady-state curve fitting, the method comprising:

[0007] Acquire unique identifiers of all sensors related to power scheduling in the microgrid, and acquire first detection data of each sensor according to the unique identifier, pre-set a time series, and establish a mapping set according to the detection time of the first detection data of each sensor and the corresponding time series;

[0008] Constructing a steady-state curve of first detection data of the sensor of each time series according to the mapping set, wherein the steady-state curve of the first detection data is constructed by curve fitting through the first detection data and the unique identifier of the sensor;

[0009] Pre-constructing the electric energy dispatching strategy for each steady-state curve of the detection data, and pre-setting the curve updating strategy for each steady-state curve of the detection data;

[0010] The second detection data of each sensor is obtained, and the second detection data is fitted to the steady-state curve of the first detection data of the corresponding time series according to the detection time, and the electric energy scheduling strategy of the steady-state curve of the first detection data is executed according to the fitting result, and the curve update strategy of the steady-state curve of the first detection data is executed.

[0011] According to one of the preferred embodiments of the present invention, the method for constructing the mapping set includes: binding the acquired unique identifier of the sensor and the corresponding first detection data, and determining the time series in which the detection time of the first detection data lies, and storing the bound unique identifier of the sensor and the corresponding first detection data in a mapping list under the corresponding time series, and obtaining the mapping list under each time series to obtain the mapping set, wherein each time series in the mapping set includes the unique identifier of each sensor and the detection data of the corresponding sensor.

[0012] According to another preferred embodiment of the present invention, the method for constructing a steady-state curve corresponding to a time series of the first detection data includes: pre-establishing a coordinate system under the time series, converting the sensor unique identifier under the time series into a fixed-value horizontal coordinate value, wherein each different sensor unique identifier corresponds to a different horizontal coordinate value, and converting the horizontal coordinate values ​​of all sensor unique identifiers under the time series into continuously increasing values, and the horizontal coordinate values ​​corresponding to the sensor unique identifiers under different time series are the same, and constructing a corresponding vertical coordinate value according to the corresponding horizontal coordinate value of the first detection data of the corresponding sensor to obtain a hash point in the coordinate system;

[0013] Each hash point represents a unique sensor identifier and detection data pair in the corresponding time series coordinate system, and a fitted steady-state curve is further constructed based on the hash points, wherein the first detection data of the steady-state curve needs to satisfy the stability rule of the mean square error in the time series, and the mean of continuous detection in the corresponding time series is taken as the first detection data.

[0014] According to another preferred embodiment of the present invention, the method for constructing the steady-state curve of the first detection data includes: performing data preprocessing on the first detection data, the data preprocessing method includes: normalizing the first detection data of all different types of sensors to obtain normalized mapping data of the first detection data of each sensor to a range of 0-1, and using the normalized mapping data of the first detection data as the ordinate value of the hash point of the corresponding sensor;

[0015] The sensor hash points obtained after preprocessing are further fitted with a preset curve function, wherein the curve function sets an initialization curve function coefficient, and n hash points are input into the curve function for fitting calculation, wherein n is all hash points in the same time series, and the curve function coefficient is calculated to obtain a fitted steady-state curve in the corresponding time series.

[0016] According to another preferred embodiment of the present invention, a method for constructing a steady-state curve of the first detection data includes: inputting the horizontal and vertical coordinate values ​​of n hash points into a curve function with preset initialization coefficients to obtain an output value of the curve function, calculating the mean square error of the n hash point output values ​​of the curve function and the corresponding first detection data actually detected, setting a first mean square error threshold, and when the mean square error of the n hash point output values ​​of the curve function and the actual first detection data is greater than the first mean square error threshold, adjusting the coefficient of the curve function until the mean square error of the n hash point output values ​​and the actual first detection data after preprocessing is less than the first mean square error threshold; and further solidifying the coefficient of the curve function to obtain the steady-state curve of the first detection data.

[0017] According to another preferred embodiment of the present invention, after the steady-state curve of the first detection data under the corresponding time series is obtained by fitting calculation, each coefficient set of the steady-state curve under the corresponding time series is further obtained, and the coefficient set of the steady-state curve is used as the control parameter of the microgrid scheduling scheme, and the electric energy scheduling strategy of the microgrid with different steady-state curve coefficient sets is pre-established. After the coefficient set of the corresponding steady-state curve is obtained by fitting the steady-state curve of the first detection data according to the second detection data, the corresponding microgrid electric energy scheduling strategy is searched according to the coefficient set of the steady-state curve, and the electric energy scheduling strategy of the microgrid is executed.

[0018] According to another preferred embodiment of the present invention, the steady-state curve updating method includes: obtaining third detection data of all sensors under another identical time series, wherein the third detection data satisfies the stability rule of the mean square error under the time series, and obtaining hash points of the third detection data after the data preprocessing of the third detection data and all sensor unique identifiers, and inputting the n hash points of the third detection data into the steady-state curve of the first detection data, and calculating the third detection data mean square error of n output values ​​of the n hash points of the steady-state curve of the first detection data and the ordinate values ​​of the hash points corresponding to the third detection data, and setting a third mean square error threshold, and when the mean square error of the third detection data is greater than the third mean square error threshold, starting the steady-state curve fitting calculation based on the third detection data, and obtaining new steady-state curve coefficients based on the third detection data.

[0019] According to another preferred embodiment of the present invention, the steady-state curve updating method includes: obtaining deletion, replacement or addition data of the corresponding microgrid load end, power generation end and storage end, and respectively setting the steady-state curve updating condition strategy for deletion, replacement or addition of the microgrid load end, power generation end and storage end, wherein the steady-state curve updating condition strategy includes at least one of deletion, replacement or addition of the microgrid load end, power generation end and storage end. When the deletion, replacement or addition of the microgrid load end, power generation end and storage end satisfies the corresponding steady-state curve updating condition strategy, the fourth detection data of the sensor under each time series is obtained, and the steady-state curve of the fourth detection data is reconstructed after further data preprocessing according to the fourth detection data and the corresponding sensor unique code, and the coefficient of the steady-state curve of the fourth detection data is obtained to construct and search for the relevant microgrid power scheduling strategy.

[0020] In order to achieve at least one of the above-mentioned invention purposes, the present invention further provides a microgrid dispatching system of steady-state curve fitting, and the system executes the above-mentioned microgrid dispatching method of steady-state curve fitting.

[0021] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned microgrid scheduling method of steady-state curve fitting. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Shown is a schematic flow chart of a microgrid dispatching method for steady-state curve fitting according to the present invention.

[0023] Figure 2 Shown is a schematic diagram of steady-state curve fitting under a time series in the present invention. DETAILED DESCRIPTION

[0024] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0025] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0026] Please combine Figure 1-Figure 2 The present invention discloses a microgrid dispatching method and system for steady-state curve fitting, and the method mainly includes the following steps: first, it is necessary to obtain unique identifications for different types of sensors for the microgrid, and the microgrid is configured with a power generation end, a power storage end and a power load end, wherein the type of the power generation end may include but is not limited to a photovoltaic power generation end, a wind power generation end, a diesel power generation end, etc., and different types of sensors are different for different power generation ends; similarly, different types of sensors may exist for the power storage end and the power load end. In the present invention, it is necessary to obtain the unique identification of each sensor of the power generation end, power storage end and power load end related to power dispatch in the microgrid, and obtain the first detection data of the corresponding sensor according to the unique identification of the sensor. The sensors related to power dispatch in the present invention may include but are not limited to voltage sensors, current sensors, temperature sensors, and battery capacity sensors. The detection data of different sensors are obtained by relevant calculation rules to obtain grid parameters such as power generation, power storage, input power and output power at different ends of the microgrid. The above calculation rules are common knowledge in the prior art, and the present invention will not be described in detail.

[0027] It should be noted that in the present invention, when the power generation end, power storage end and power load end are not replaced, substituted or abandoned, their own grid parameters are often in a stable state for a period of time. For example, the photovoltaic power generation end usually absorbs solar energy during the day and converts it into electrical energy and inputs it into the corresponding power storage end for storage, while at night, the load end will increase a certain amount of electricity consumption due to turning on the lights and cooking. The power generation, power consumption, storage and scheduling of the above-mentioned different ends are in a stable state when the external environment does not change significantly. Therefore, there is no need to monitor the relevant sensors of the power generation end, power storage end and power load end in real time, and the real-time monitoring of all the relevant sensors of the power generation end, power storage end and power load end also increases the energy consumption problem inside the microgrid. It is also worth noting that since the microgrid has a stable state within a certain period of time, when the relevant sensors are damaged, the stable state should not be damaged. However, the actual situation is that when the sensors monitor in real time and perform real-time scheduling of electric energy, the relevant sensors will be damaged and will immediately affect the electric energy scheduling strategy. This part of the impact is negative, which reduces the effect of electric energy scheduling.

[0028] Therefore, the present invention constructs steady-state curves of different time series based on all sensors related to power dispatching in the microgrid and the detection data of the corresponding sensors, and executes the power dispatching strategy of the microgrid through the steady-state curve. In the present invention, after obtaining the steady-state curve, there is no need for real-time monitoring with relevant sensors, and the corresponding stable state power dispatching can be executed after the sensor performs a detection, thereby greatly reducing the energy consumption of the sensor in the microgrid and improving the energy-saving effect of the microgrid. And when the steady-state curve is used to execute the corresponding power dispatching strategy in the present invention, there is no need to refer to the faulty sensor in the microgrid within a certain period of time, thereby reducing the impact of the faulty sensor on the power dispatching strategy of the microgrid.

[0029] Specifically, the method for constructing a steady-state curve of the first detection data includes: first, it is necessary to construct a curve function coordinate system, and obtain the unique identifier of the sensor related to the power scheduling in the microgrid. Each sensor unique identifier is further converted into a fixed value of the horizontal coordinate, and the fixed value of the horizontal coordinate corresponding to each sensor unique identifier is unique and continuous, which is used to construct hash points in the curve function coordinate system. For example, the value range of the horizontal coordinate in the curve function coordinate system can be defined as [1,2,34,5....n], where n∈Z is a positive integer, and n is a continuous value in the function coordinate system. The n value maps a unique identifier of a sensor, and the horizontal coordinate value of the curve function coordinate system mapped by the unique identifier of each sensor is one-to-one. It should be noted that, in the present invention, after the first detection data of each sensor is collected, the first detection data is further preprocessed, wherein the data preprocessing method includes: normalizing each sensor data according to its type, wherein the normalization method can be implemented by including but not limited to the minimum-maximum normalization (Min-Max Normalization) or Z-score normalization (Z-Score Normalization), wherein the minimum-maximum normalization (Min-MaxNormalization) needs to obtain the maximum and minimum values ​​of the corresponding type of sensor data, and use the difference between the maximum and minimum values ​​as the denominator, and use the corresponding first detection data as the numerator for normalization; wherein the Z-score normalization method is based on the mean (μ) and standard deviation (σ) of the original data for normalization, and converts the data into a distribution with a mean of 0 and a standard deviation of 1. The above two normalization methods are only prior art, and the present invention will not elaborate on them.

[0030] Furthermore, after the normalization processing of the first detection data is completed, a hash point in the curve function coordinate system is further constructed according to the sensor unique identifier and the first detection data after the normalization processing of the corresponding sensor, wherein the horizontal coordinate value of the hash point is the sensor unique coordinate value for the horizontal coordinate value conversion, and the vertical coordinate value of the hash point is the first detection data value for the normalization preprocessing. Define x n is the corresponding horizontal coordinate value, y n is the corresponding ordinate value, n represents the corresponding sensor unique identifier, so the hash point of the first detection data can be expressed as P n =(x n ,y n ). The hash points are discontinuous values ​​in the coordinate system, so it is necessary to construct a related curve function to fit multiple hash points to obtain the corresponding steady-state curve.

[0031] It should be noted that an important condition for constructing the steady-state curve in the present invention is that the first detection data is in a stable state under the corresponding time series. That is to say, the first detection data needs to meet certain mean square error conditions under the corresponding time series, so that the mean square error of the same sensor data of the first detection data cannot exceed a certain mean square error threshold. In the present invention, it is necessary to perform multiple detections of the first detection data on each sensor under the time series, calculate the mean square error of the first detection data of each sensor itself, and judge whether each current sensor first detection data is in a stable state based on the mean square error threshold. If the first detection data meets the stability condition, the average value of the multiple detections of the corresponding sensor in the time series is used as the first detection data.

[0032] It is worth mentioning that the time series described in the present invention can be set according to the power dispatching frequency of the microgrid, for example, a time series with a time range of 5 minutes, 10 minutes or 30 minutes can be set, and the length of the time series is no longer specifically limited in the present invention. The present invention needs to further set the period of the time series. In the present invention, 0 o'clock every day is used as the starting point of a periodic time series, and 24 o'clock every day is used as the end of a periodic time series. A new day generates a new periodic time series, wherein the length of each time series of the new periodic time series is the same as the length of the time series of the previous period, and the time series of the new period can inherit the steady-state curve of the corresponding time series of the previous period in a stable state, so the steady-state curve can realize the periodic execution of the power dispatching strategy. Of course, in another preferred embodiment of the present invention, according to the different service objects and environments of the microgrid, the present invention can set different time lengths as the period of the time series, and the present invention will not be described in detail.

[0033] Furthermore, in the present invention, after obtaining all the hash point data in the corresponding time series, an initialized curve function is further constructed, such as Figure 2 The curve function fitting diagram shown in the figure, A represents the steady-state curve of the first detection data of the corresponding time series, B represents the steady-state curve of the third detection data, Cn represents the corresponding hash point of the first detection data of the corresponding time series, because the hash point is normalized, the output value F (x n )∈[0,1], the initialized curve function has an initialization coefficient. In the present invention, a sine and cosine function can be selected as the initialized curve function in the present invention, for example, the curve function can be F(x n )=a1*cos(x n / 2Π+θ1)+b1*sin(x n / 2Π+θ2)+c1, where a1, b1, c1, θ1 and θ2 are initialization coefficients. In other preferred embodiments of the present invention, a polynomial curve function can be constructed, such as F(x n )= , where a1, b1, c1 and k1 are all initialization coefficients. Based on the initialization coefficients, the present invention inputs the n hash points into the curve function for fitting calculation, and calculates the output value F (x n ) and the true value y of the hash point n The mean square error The coefficient of the curve function is adjusted according to the mean square error E until the mean square error meets a minimum or certain threshold value, and the coefficient a of the curve function after fitting can be obtained. s 、b s 、c s and k s etc., solidify the curve coefficient a that meets the fitting conditions s 、b s 、c s and k s Etc., thus obtaining the steady-state curve F s (x n ). Since the functional formulas are different after fitting with different curve functions, the present invention will not explain the steady-state curve of the specific curve function fitting in detail.

[0034] It should be noted that the above-mentioned steady-state curve is obtained based on the same time series. Therefore, when the time series are different, it is necessary to calculate the steady-state curves under different time series so that each time series has a corresponding steady-state curve to control the relevant power dispatching scheme of the microgrid. The control method of the microgrid power dispatching strategy based on the steady-state curve in the present invention includes the following steps: when the first detection data is obtained by fitting and calculating the steady-state curve under the corresponding time series, each coefficient set of the steady-state curve under the corresponding time series is further obtained, and the coefficient set of the steady-state curve is used as the control parameter of the microgrid dispatching scheme, and the power dispatching strategy of the microgrid with different steady-state curve coefficient sets is pre-established. When the coefficient set of the corresponding steady-state curve is obtained by fitting and calculating the steady-state curve of the first detection data according to the second detection data, the corresponding microgrid power dispatching strategy is searched according to the coefficient set of the steady-state curve, and the power dispatching strategy of the microgrid is executed. In the present invention, the coefficient set of the relevant steady-state curve is used to dispatch the power of the microgrid, and the coefficient set can use the approximate value method to judge whether the corresponding steady-state curve meets the corresponding microgrid dispatching strategy. The microgrid dispatching strategy corresponding to the steady-state curve coefficient set closest to the steady-state curve can be selected. In the present invention, the coefficient set of the microgrid steady-state curve implies the data of the electric energy dispatching state of the microgrid under a certain stable state. The data is mapped and represented in the form of a coefficient set in the present invention. At this time, accurate and stable microgrid dispatching can be achieved without turning on all sensors for real-time monitoring. Even if there are certain faults in the relevant sensors of the microgrid, it will not have a certain impact on the overall dispatching of the microgrid.

[0035] It should be noted that the steady-state curve data obtained from the first detection data is used as the steady-state curve data of the corresponding time series, and n hash point data of the second detection data of all sensors under the actual detection of the corresponding time series are further obtained, and the n hash point data of the second detection data are input into the steady-state curve to determine whether the output of the steady-state curve function of the corresponding realization sequence is less than the mean square error threshold E s If the condition is met, the microgrid dispatching strategy mapped by the corresponding steady-state curve is executed until the next time series, when all sensors are detected again to obtain the hash point values ​​of the second detection data of the next time series to see if they meet the steady-state curve of the next time series, until the complete cycle of the time series is detected to obtain the hash point values ​​of the second detection data, and the microgrid dispatching strategy of the steady-state curve under the corresponding time series is executed.

[0036] Furthermore, in another preferred embodiment of the present invention, since the microgrid itself may be affected by factors such as equipment updates or equipment aging, which may disrupt the original stable scheduling state of the microgrid, the present invention further provides a method for updating the steady-state curve of the relevant microgrid, so that the present invention can maintain stable microgrid scheduling while taking into account the flexibility of the microgrid itself, thereby avoiding the problem of overly stable microgrid scheduling being incompatible with scheduling when the microgrid environment changes. The updating method of the steady-state curve includes: obtaining the third detection data of all sensors under another same time series, wherein the third detection data satisfies the stability rule of the mean square error under the time series, and obtaining the hash points of the third detection data after the data preprocessing of the third detection data and the unique identifiers of all sensors, and inputting the n hash points of the third detection data into the steady-state curve of the first detection data, and calculating the mean square error of the third detection data of the n output values ​​of the n hash points of the steady-state curve of the first detection data and the ordinate value of the hash points corresponding to the third detection data, and setting the third mean square error threshold, when the mean square error of the third detection data is greater than the third mean square error threshold, the steady-state curve fitting calculation based on the third detection data is started, and the new steady-state curve coefficient based on the third detection data is obtained. In this embodiment, the stability rule of the mean square error can be set to when the hash points of each sensor of the third detection data itself meet the mean square error under multiple detections less than the preset mean square error threshold. The third detection data is the stability change of the demand, power generation or storage end when there is no increase or decrease in the related equipment of the internal power dispatching of the microgrid.

[0037] In another preferred embodiment of the present invention, the update of the steady-state curve can also be based on the deletion, replacement or addition of the internal equipment of the microgrid. The equipment in the present invention is not a sensor, but a power generation equipment, load-end equipment, energy storage equipment, etc. related to the microgrid scheduling. Based on the change of the internal equipment of the microgrid, the present invention performs the following steady-state curve update operation for each time series: obtaining the deletion, replacement or addition data of the corresponding microgrid load end, power generation end and storage end, and respectively setting the steady-state curve update condition strategy for the deletion, replacement or addition of the microgrid load end, power generation end and storage end, wherein the steady-state curve update condition strategy includes at least one of the deletion, replacement or addition of the microgrid load end, power generation end and storage end, when the deletion, replacement or addition of the microgrid load end, power generation end and storage end meets the corresponding steady-state curve update condition strategy, then the fourth detection data of the sensor under each time series is obtained, and the steady-state curve of the fourth detection data is reconstructed after further data preprocessing according to the fourth detection data and the corresponding sensor unique code, and the coefficient of the steady-state curve of the fourth detection data is obtained to construct and search for the relevant microgrid power scheduling strategy. In this embodiment, the flexibility of the steady-state curve can be effectively improved, while also reducing the problem of excessive power consumption in the microgrid monitored in real time by the sensor.

[0038] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0039] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0040] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A microgrid dispatching method based on steady-state curve fitting, characterized in that: The method comprises: Acquire unique identifiers of all sensors related to power scheduling in the microgrid, and acquire first detection data of each sensor according to the unique identifier, pre-set a time series, and establish a mapping set according to the detection time of the first detection data of each sensor and the corresponding time series; Constructing a steady-state curve of first detection data of the sensor of each time series according to the mapping set, wherein the steady-state curve of the first detection data is constructed by curve fitting through the first detection data and the unique identifier of the sensor; Pre-constructing the electric energy dispatching strategy for each steady-state curve of the detection data, and pre-setting the curve updating strategy for each steady-state curve of the detection data; The second detection data of each sensor is obtained, and the second detection data is fitted to the steady-state curve of the first detection data of the corresponding time series according to the detection time, and the electric energy scheduling strategy of the steady-state curve of the first detection data is executed according to the fitting result, and the curve update strategy of the steady-state curve of the first detection data is executed.

2. A microgrid dispatching method based on steady-state curve fitting according to claim 1, characterized in that: The method for constructing the mapping set includes: binding the acquired unique identifier of the sensor and the corresponding first detection data, determining the time series in which the detection time of the first detection data is located, and storing the bound unique identifier of the sensor and the corresponding first detection data in a mapping list under the corresponding time series, obtaining the mapping list under each time series to obtain the mapping set, wherein each time series in the mapping set includes the unique identifier of each sensor and the detection data of the corresponding sensor.

3. The microgrid dispatching method of steady-state curve fitting according to claim 1 is characterized in that: The method for constructing a steady-state curve corresponding to the time series of the first detection data includes: pre-establishing a coordinate system under the time series, converting the sensor unique identifier under the time series into a fixed-value horizontal coordinate value, wherein each different sensor unique identifier corresponds to a different horizontal coordinate value, and converting the horizontal coordinate values ​​of all sensor unique identifiers under the time series into continuously increasing values, and the horizontal coordinate values ​​corresponding to the sensor unique identifiers under different time series are the same, and constructing a corresponding vertical coordinate value according to the corresponding horizontal coordinate value of the first detection data of the corresponding sensor to obtain a hash point in the coordinate system; Each hash point represents a unique sensor identifier and detection data pair in the corresponding time series coordinate system, and a fitted steady-state curve is further constructed based on the hash points, wherein the first detection data of the steady-state curve needs to satisfy the stability rule of the mean square error in the corresponding time series, and the average of multiple continuous detections of the corresponding sensor in the corresponding time series is taken as the first detection data.

4. The microgrid dispatching method of steady-state curve fitting according to claim 3 is characterized in that: The method for constructing the steady-state curve of the first detection data includes: performing data preprocessing on the first detection data, and the data preprocessing method includes: normalizing the first detection data of all different types of sensors to obtain normalized mapping data of the first detection data of each sensor to a range of 0-1, and using the normalized mapping data of the first detection data as the ordinate value of the hash point of the corresponding sensor; The sensor hash points obtained after preprocessing are further fitted with a preset curve function, wherein the curve function sets an initialization curve function coefficient, and n hash points are input into the curve function for fitting calculation, wherein n is all hash points in the same time series, and the curve function coefficient is calculated to obtain a fitted steady-state curve in the corresponding time series.

5. A microgrid dispatching method based on steady-state curve fitting according to claim 4, characterized in that: The method for constructing the steady-state curve of the first detection data includes: inputting the horizontal and vertical coordinate values ​​of n hash points into a curve function with preset initialization coefficients to obtain an output value of the curve function, calculating the mean square error between the n hash point output values ​​of the curve function and the first detection data actually detected, setting a first mean square error threshold, and when the mean square error between the n hash point output values ​​of the curve function and the actual first detection data is greater than the first mean square error threshold, adjusting the coefficient of the curve function until the mean square error between the n hash point output values ​​and the actual first detection data after preprocessing is less than the first mean square error threshold; and further solidifying the coefficient of the curve function to obtain the steady-state curve of the first detection data.

6. The microgrid dispatching method of steady-state curve fitting according to claim 1 is characterized in that: When the first detection data is fitted to obtain a steady-state curve under a corresponding time series, each coefficient set of the steady-state curve under the corresponding time series is further obtained, and the coefficient set of the steady-state curve is used as a control parameter of a microgrid scheduling scheme, and an electric energy scheduling strategy of a microgrid with different steady-state curve coefficient sets is pre-established. When the steady-state curve of the first detection data is fitted and calculated according to the second detection data to obtain a coefficient set of the corresponding steady-state curve, the corresponding electric energy scheduling strategy of the microgrid is searched according to the coefficient set of the steady-state curve, and the electric energy scheduling strategy of the microgrid is executed.

7. The microgrid dispatching method of steady-state curve fitting according to claim 3 is characterized in that: The steady-state curve updating method includes: obtaining third detection data of all sensors under another identical time series, wherein the third detection data satisfies the stability rule of the mean square error under the corresponding time series, and obtaining hash points of the third detection data after data preprocessing of the third detection data and all sensor unique identifiers, and inputting n hash points of the third detection data into the steady-state curve of the first detection data, and calculating the third detection data mean square error of n output values ​​of the n hash points of the steady-state curve of the first detection data and the ordinate values ​​of the hash points corresponding to the third detection data, and setting a third mean square error threshold, and when the mean square error of the third detection data is greater than the third mean square error threshold, starting the steady-state curve fitting calculation based on the third detection data, and obtaining new steady-state curve coefficients based on the third detection data.

8. The microgrid dispatching method of steady-state curve fitting according to claim 1 is characterized in that: The steady-state curve updating method includes: obtaining deletion, replacement or addition data of the corresponding microgrid load end, power generation end and storage end, and respectively setting the steady-state curve updating condition strategy for deletion, replacement or addition of the microgrid load end, power generation end and storage end, wherein the steady-state curve updating condition strategy includes at least one of deletion, replacement or addition of the microgrid load end, power generation end and storage end. When the deletion, replacement or addition of the microgrid load end, power generation end and storage end meets the corresponding steady-state curve updating condition strategy, the fourth detection data of the sensor under each time series is obtained, and the steady-state curve of the fourth detection data is reconstructed after further data preprocessing according to the fourth detection data and the corresponding sensor unique code, and the coefficient of the steady-state curve of the fourth detection data is obtained to construct and search for the relevant microgrid power scheduling strategy.

9. A microgrid dispatching system with steady-state curve fitting, characterized in that: The system executes a microgrid scheduling method for steady-state curve fitting as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a microgrid scheduling method for steady-state curve fitting as described in any one of claims 1-8.

Images