Distributed energy scheduling optimization method

Abstract

The invention discloses a distributed energy scheduling optimization method, which relates to the technical field of energy scheduling, and comprises the following steps: obtaining all regions in a to-be-tested cell, marking each region, and obtaining power time sequence data and power scheduling influence data of each region; drawing a broken line graph according to the frequency and generating capacity data of each unit in each time period, and analyzing through a Pearson's correlation coefficient to obtain the correlation between the frequency and the generating capacity; obtaining a power grid stability coefficient based on a machine learning algorithm according to the frequency state and the power dispatching influence data; controlling the generating capacity to change the frequency state according to the correlation between the frequency state and the generating capacity so as to obtain the value of a power grid stability coefficient in different frequency states; by obtaining the stability of energy scheduling, the efficiency and stability of distributed energy scheduling are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching, and more specifically, to a distributed energy dispatching optimization method. Background Art

[0002] Distributed energy dispatch technology is a key solution to meet the challenges of modern power systems, aiming to optimize resource allocation and improve system reliability and economy. With the rapid development of renewable energy such as solar and wind power, power production is gradually shifting from a centralized mode to a distributed mode. Distributed energy systems are usually composed of multiple small-scale power generation units, including photovoltaic systems on residential roofs, community wind turbines, and on-board energy storage devices for electric vehicles.

[0003] In addition, the application of smart grid technology makes the integration and management of distributed energy more efficient. Through advanced sensors, communication technology and data analysis tools, the dispatching system can obtain system status information in real time, so as to respond quickly and optimize energy flow.

[0004] The above disclosed technical solutions have at least the following technical problems: Traditional distributed energy scheduling is based on static load prediction, ignoring the real-time changes of system frequency, resulting in frequency fluctuations. In addition, during the energy scheduling process, power loss is often simplified or ignored, focusing only on the direct balance between power generation and load, which reduces the efficiency and stability of distributed energy scheduling. There is also a lack of automatic perception and adjustment of the power grid state, and excessive reliance on manual intervention, which reduces the response speed of the scheduling system. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a distributed energy scheduling optimization method, by obtaining all areas within the cell to be tested, labeling each area and obtaining the power time series data and power scheduling impact data of each area, wherein the power time series data includes the frequency status and power generation in each time period; a line graph is drawn according to the frequency and power generation data of each area in each time period, and the correlation between frequency and power generation is obtained through Pearson correlation coefficient analysis; a grid stability coefficient is obtained based on the frequency status and power scheduling impact data based on a machine learning algorithm; according to the correlation between the frequency status and power generation, the size of the power generation is controlled to change the frequency status, thereby obtaining the value of the grid stability coefficient under different frequency states to solve the problem of low efficiency and stability of distributed energy scheduling.

[0006] To achieve the above object, the present invention provides the following technical solutions: The distributed energy dispatch optimization method includes: obtaining all areas within the cell to be tested, labeling each area and obtaining the power time series data and power dispatch impact data of each area, wherein the power time series data includes the frequency status and power generation in each time period; drawing a line graph according to the frequency and power generation data of each area in each time period, and obtaining the correlation between frequency and power generation through Pearson correlation coefficient analysis; obtaining the grid stability coefficient based on the frequency status and power dispatch impact data based on a machine learning algorithm; and according to the correlation between the frequency status and power generation, controlling the size of power generation to change the frequency status, thereby obtaining the value of the grid stability coefficient under different frequency states.

[0007] In a preferred embodiment, the power time series data includes the frequency status and power generation of each time period, specifically: collecting historical frequency status and power generation data in each area; performing data cleaning on the collected historical frequency status and power generation data, cleaning up missing values ​​and outliers, and deleting data with frequency deviation exceeding a preset threshold based on a machine learning model; and classifying and counting the cleaned frequency status and power generation data according to the time period and area of ​​each hour.

[0008] In a preferred embodiment, the power dispatch influencing data includes work electromagnetic torque, and the specific steps for obtaining the work electromagnetic torque are as follows: obtain the performance parameters of the generator, the performance parameters including magnetic flux, device constants, armature resistance and power supply voltage; collect multiple groups of generator speeds in the same time period, and smooth the generator speed data through time series analysis to obtain the characteristic values ​​therein; calculate the back electromotive force based on the preset back electromotive force calculation formula according to the generator speed, armature resistance and power supply voltage; calculate the armature current based on the armature current formula according to the back electromotive force, power supply voltage and armature resistance; obtain the direction of the current and magnetic field through the right-hand rule and the Hall effect sensor, and obtain the angle between the current and the magnetic field according to the direction of the current and the magnetic field; calculate the electromagnetic torque based on the preset electromagnetic torque formula according to the device constant, magnetic flux, armature current and the angle between the current and the magnetic field.

[0009] In a preferred embodiment, the power dispatch influencing data includes a power balance constraint state, and the specific steps for obtaining the power balance constraint state are as follows: obtain the total number of power generation units, the total number of loads, and the power generation power of the generator; obtain the power consumption in each time period through the power system, and calculate the load power in each time period according to the load power formula; perform seasonal and periodic detection on the collected load power, and clear abnormal data; obtain the resistance and reactance data of the transmission line, and perform power flow analysis in combination with the network topology to obtain the power loss in the transmission process; calculate the power balance constraint state based on the power loss power, load power and power generation power in the transmission process and the power balance constraint model formula.

[0010] In a preferred embodiment, the frequency and power generation data of each area in each time period are plotted into a line graph, and the correlation between frequency and power generation is obtained by Pearson correlation coefficient analysis, specifically: the grid frequency and the power generation of the generator in each time period are obtained; the horizontal axis x-axis is the power generation of the generator, and the y-axis is the frequency of the grid, and a line graph is plotted.

[0011] In a preferred embodiment, the correlation between the frequency state and the power generation is used to control the size of the power generation to change the frequency state, thereby obtaining the value of the grid stability coefficient under different frequency states, as follows: if the value of the stability coefficient is lower than the set threshold, the frequency of the grid is increased by increasing the power generation of the generator, thereby improving the stability of the system; when the value of the stability number of an area is lower than the preset value and there are no idle generators, other regional generators with stability coefficients higher than the preset value will be called, and the overall stability will be recalculated; if after n adjustments, the stability is still lower than the set threshold, an early warning will be issued to remind the administrator that external manual maintenance is required; when the maintenance of each area is completed, the stability of each area and the overall stability of the community will be re-evaluated.

[0012] The technical effects and advantages of the distributed energy scheduling optimization method of the present invention are as follows: 1. The present invention can adjust the power generation in real time by analyzing the correlation between the frequency state and the power generation, thereby optimizing the stability of the power grid. When the power grid frequency is low, the power generation is increased to increase the frequency to ensure the stable operation of the power grid. This process dynamically adjusts the power generation through machine learning algorithms and data analysis, effectively solving the problem of power grid instability.

[0013] 2. The present invention conducts a detailed analysis of the power time series data of different regions, and combines the machine learning model to predict the stability and demand of the power grid. The system can accurately adjust energy distribution, reduce energy waste, and optimize energy efficiency. This method can effectively manage the load and power generation of each unit building and improve the overall energy scheduling efficiency. At the same time, by real-time monitoring of key parameters such as frequency status, power generation, power balance, etc., the system promptly detects abnormal conditions and corrects the imbalance of the power grid by adjusting the power generation or calling the backup generator, thereby avoiding the resulting power system failure. If the system still cannot achieve stability after multiple adjustments, it will issue an early warning to prompt the administrator to conduct manual inspection and repair, thereby reducing the risk of large-scale failures in the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a structural schematic diagram of the distributed energy scheduling optimization method of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1, Figure 1 The present invention provides a distributed energy scheduling optimization method, which includes the following steps: S1, obtain all areas within the cell to be tested, label each area and obtain the power time series data and power dispatch impact data of each area, wherein the power time series data includes the frequency status and power generation in each time period.

[0017] In this embodiment, the power time series data and power dispatch impact data of each area are collected according to the regional division.

[0018] The power time series data includes the frequency state and power generation in each time period, specifically: Collect historical frequency status and power generation data in each area; Clean the collected historical frequency status and power generation data to remove missing values ​​and outliers. At the same time, based on the machine learning model, delete the data whose frequency deviation exceeds the preset threshold. The cleaned frequency status and power generation data are classified and counted according to the time period and area of ​​each hour.

[0019] It should be noted that the frequency deviation exceeds the preset threshold, which is 3Hz to 5Hz under normal conditions. When the frequency deviation exceeds the preset threshold, it will cause fluctuations in the stability of the power grid, leading to large-scale power failures. At the same time, when the transformer works under frequency deviation, it will cause the output voltage waveform to be distorted, affecting the operating efficiency and safety of the transformer. Through the machine learning model, the data with frequency deviation exceeding the threshold is deleted and the data under normal conditions is retained, effectively ensuring the scientificity and reliability of the data.

[0020] In this embodiment, the power dispatch impact data includes power loss and power balance constraint status, specifically: Electromagnetic torque is the torque generated by the action of current in a magnetic field. It is an important parameter in the working process of the motor and determines the starting, acceleration and load capacity of the motor. When current flows through a conductor, a magnetic field is generated around it. If the conductor is placed in an external magnetic field such as the magnetic field generated by a permanent magnet or a motor stator, the interaction between the current and the magnetic field will generate torque.

[0021] The specific steps of obtaining the electromagnetic torque are as follows: Acquiring performance parameters of the generator, the performance parameters including magnetic flux, device constant, armature resistance and power supply voltage; Collect multiple groups of generator speed data in the same time period, smooth the generator speed data through time series analysis, and obtain the characteristic values; According to the rotation speed, armature resistance and power supply voltage of the generator, the back electromotive force is calculated based on a preset back electromotive force calculation formula; According to the back electromotive force, the power supply voltage and the armature resistance, based on the armature current formula, the armature current is calculated; The directions of the current and magnetic field are obtained by the right-hand rule and the Hall effect sensor, and the angle between the current and magnetic field is obtained according to the directions of the current and magnetic field; The electromagnetic torque is calculated based on the device constant, magnetic flux, armature current and the angle between the current and the magnetic field and based on a preset electromagnetic torque formula.

[0022] The specific calculation formula of the electromagnetic torque is as follows:

[0023] The specific calculation formula of the armature current is as follows:

[0024] The specific calculation formula of the armature current is as follows:

[0025] In the formula, is the electromagnetic torque, is the device constant, is the magnetic flux, is the armature current, is the angle between the current and the magnetic field, is pi, is the back EMF, is the generator supply voltage, is the armature resistance, is the speed of the generator.

[0026] Furthermore, high electromagnetic torque enables the motor to respond quickly to load changes and improve the dynamic stability of the system. In power dispatching, if the torque of the motor can be adjusted quickly, the system balance will be quickly restored when the load changes suddenly, preventing the frequency from deviating too much. Low electromagnetic torque requires additional equipment to compensate, which further increases the complexity and energy consumption of the system. When the load suddenly increases, insufficient torque will cause the motor speed to drop, affecting the system frequency.

[0027] The power balance constraint state is an important concept in power system analysis and optimization. It is mainly used to ensure the balance of supply and demand in the power system during operation. The basic concept is that at any given point in time, the total power generation in the power system must be equal to the total load power plus the transmission loss.

[0028] The specific steps for obtaining the power balance constraint state are as follows: Obtain the total number of power generation units, the total number of loads, and the power generation of the generator; The power consumption in each time period is obtained through the power system, and the load power in each time period is calculated according to the load power formula; Conduct seasonal and periodic detection on the collected load power and remove abnormal data; Obtain the resistance and reactance data of the transmission line, perform power flow analysis based on the network topology, and obtain the power loss during the transmission process; According to the power loss, load power and power generation in the transmission process, based on the power balance constraint model formula, the power balance constraint state is calculated.

[0029] The specific calculation formula of the power balance constraint state is as follows:

[0030] The specific calculation formula of the power loss during the transmission process is as follows:

[0031] In the formula, is the power balance constraint state, is the power generated by the ith generator, n is the total number of generating units, is the power demand of the jth load, m is the total number of loads, is the power loss during the transmission process. represents the resistance of the transmission line, represents the power output of the kth generator.

[0032] It should be noted that It is an important indicator that reflects the balance between power generation capacity and load. It ensures the reliability and stability of the system by monitoring and adjusting power generation capacity, load and loss. A high value indicates sufficient power supply, while a low or negative A low value indicates a potential power shortage risk.

[0033] S2, drawing a line graph based on the frequency and power generation data of each unit in each time period, and obtaining the correlation between frequency and power generation through Pearson correlation coefficient analysis.

[0034] In this embodiment, a line graph is drawn according to the frequency and power generation data of each area in each time period, and the correlation between frequency and power generation is obtained by Pearson correlation coefficient analysis, specifically: the grid frequency and the power generation of the generator in each time period are obtained; the horizontal axis x-axis is the power generation of the generator, and the y-axis is the frequency of the grid, and a line graph is drawn.

[0035] The specific calculation formula of the Pearson correlation coefficient is as follows:

[0036] The specific calculation formula for the correlation between the frequency and the power generation is as follows:

[0037] In the formula, is the Pearson correlation coefficient, is the number of data points, is the sum of the frequencies, is the sum of the power generation, is the sum of the product of frequency and power generation, is the sum of the squares of the frequencies, is the sum of the squares of the power generation, is the frequency, is the frequency response coefficient of the system, It is the amount of electricity generated.

[0038] It should be noted that the value range of r is [-1,1]. If r is close to 1, it indicates a strong positive correlation; if it is close to -1, it indicates a strong negative correlation; if it is close to 0, it indicates no correlation. In addition, the frequency is positively correlated with the power generation of the generator. When the stability of the energy dispatching system decreases, it is necessary to increase the power generation of the power grid to increase the frequency of the power grid. S3, according to the frequency state and the power dispatching impact data, the power grid stability coefficient is obtained based on the machine learning algorithm.

[0039] In this embodiment, the grid stability coefficient is obtained based on the frequency state and the power dispatching impact data based on a machine learning algorithm, as follows: The specific calculation formula of the power grid stability coefficient is as follows:

[0040] In the formula, is the grid stability factor, is the electromagnetic torque, is the current grid frequency, It indicates the rated frequency of the power grid. is the power balance constraint state, It is the power loss during the transmission process.

[0041] It should be noted that the value range of the grid stability coefficient is [0,1]. The higher the value of the grid stability coefficient, the stronger the stability of the energy dispatch. If the value of the grid stability coefficient is lower than the preset value, it is necessary to change the frequency state by increasing the power generation to enhance the grid stability coefficient.

[0042] S4, according to the correlation between the frequency state and the power generation, the size of the power generation is controlled to change the frequency state, so as to obtain the value of the grid stability coefficient under different frequency states.

[0043] In this embodiment, the correlation between the frequency state and the power generation is used to control the power generation to change the frequency state, thereby obtaining the value of the grid stability coefficient under different frequency states. The specific steps are as follows: Obtain the stability coefficient of each area, and sort each area in descending order according to the stability coefficient, to obtain a descending sorting table and the overall stability of the community; If the value of a regional stability factor is lower than the set threshold, the frequency of the power grid is increased by increasing the power generation of the generators, thereby improving the stability of the regional system; When the stability factor of a region is lower than the preset value and there are no idle generators, other regional generators with stability factors higher than the preset value will be called according to the descending sorting table; Get the stability of each adjusted region, re-sort them and recalculate the overall stability; If the best stability is achieved after n adjustments, and the stability is still lower than the set threshold, an early warning will be issued to remind the administrator that external manual maintenance is required; After each area is inspected, the stability of each area and the stability of the community as a whole will be re-evaluated.

[0044] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0045] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0046] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0047] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0049] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A distributed energy scheduling optimization method, characterized in that: include: Acquire all areas within the cell to be tested, label each area and acquire power time series data and power dispatch impact data of each area, wherein the power time series data includes frequency status and power generation in each time period; A line graph is drawn based on the frequency and power generation data of each area in each time period, and the correlation between frequency and power generation is obtained through Pearson correlation coefficient analysis; Obtaining a grid stability coefficient based on a machine learning algorithm according to the frequency state and power dispatch impact data; According to the correlation between the frequency state and the power generation, the power generation is controlled to change the frequency state, thereby obtaining the value of the grid stability coefficient under different frequency states.

2. The distributed energy scheduling optimization method according to claim 1 is characterized in that: The power time series data includes the frequency state and power generation in each time period, specifically: Collect historical frequency status and power generation data in each area; Clean the collected historical frequency status and power generation data to remove missing values ​​and outliers. At the same time, based on the machine learning model, delete the data whose frequency deviation exceeds the preset threshold. The cleaned frequency status and power generation data are classified and counted according to the time period and area of ​​each hour.

3. The distributed energy scheduling optimization method according to claim 2 is characterized in that: The power dispatching influence data includes the work electromagnetic torque, and the specific steps of obtaining the work electromagnetic torque are as follows: Acquiring performance parameters of the generator, the performance parameters including magnetic flux, device constant, armature resistance and power supply voltage; Collect multiple groups of generator speed data in the same time period, smooth the generator speed data through time series analysis, and obtain the characteristic values; According to the rotation speed, armature resistance and power supply voltage of the generator, the back electromotive force is calculated based on a preset back electromotive force calculation formula; According to the back electromotive force, the power supply voltage and the armature resistance, based on the armature current formula, the armature current is calculated; The directions of the current and magnetic field are obtained by the right-hand rule and the Hall effect sensor, and the angle between the current and magnetic field is obtained according to the directions of the current and magnetic field; The electromagnetic torque is calculated based on the device constant, magnetic flux, armature current and the angle between the current and the magnetic field and based on a preset electromagnetic torque formula.

4. The distributed energy scheduling optimization method according to claim 3 is characterized in that: The power dispatching impact data includes a power balance constraint state, and the specific steps for obtaining the power balance constraint state are as follows: Obtain the total number of power generation units, the total number of loads, and the power generation of the generator; The power consumption in each time period is obtained through the power system, and the load power in each time period is calculated according to the load power formula; Conduct seasonal and periodic detection on the collected load power and remove abnormal data; Obtain the resistance and reactance data of the transmission line, perform power flow analysis based on the network topology, and obtain the power loss during the transmission process; According to the power loss, load power and power generation in the transmission process, based on the power balance constraint model formula, the power balance constraint state is calculated.

5. The distributed energy scheduling optimization method according to claim 4 is characterized in that: The frequency and power generation data of each area in each time period are plotted into a line graph, and the correlation between frequency and power generation is obtained by Pearson correlation coefficient analysis, specifically: Obtain the grid frequency and generator power generation in each time period; A line graph is drawn with the x-axis being the power generation of the generator and the y-axis being the frequency of the power grid.

6. The distributed energy scheduling optimization method according to claim 5 is characterized in that: The correlation between the frequency state and the power generation is used to control the power generation to change the frequency state, thereby obtaining the value of the grid stability coefficient under different frequency states, as follows: Obtain the stability coefficient of each area, and sort each area in descending order according to the stability coefficient, to obtain a descending sorting table and the overall stability of the community; If the value of a regional stability factor is lower than the set threshold, the frequency of the power grid is increased by increasing the power generation of the generators, thereby improving the stability of the regional system; When the stability factor of a region is lower than the preset value and there are no idle generators, other regional generators with stability factors higher than the preset value will be called according to the descending sorting table; Get the stability of each adjusted region, re-sort them and recalculate the overall stability; If the best stability is achieved after n adjustments, and the stability is still lower than the set threshold, an early warning will be issued to remind the administrator that external manual maintenance is required; After each area is inspected, the stability of each area and the stability of the community as a whole will be re-evaluated.

7. The distributed energy scheduling optimization method according to claim 6 is characterized in that: The specific calculation formula of the electromagnetic torque is as follows: The specific calculation formula of the armature current is as follows: The specific calculation formula of the armature current is as follows: In the formula, is the electromagnetic torque, is the device constant, is the magnetic flux, is the armature current, is the angle between the current and the magnetic field, is pi, is the back EMF, is the generator supply voltage, is the armature resistance, is the speed of the generator.

8. The distributed energy scheduling optimization method according to claim 7 is characterized in that: The specific calculation formula of the power balance constraint state is as follows: The specific calculation formula of the power loss during the transmission process is as follows: In the formula, is the power balance constraint state, is the power generated by the ith generator, n is the total number of generating units, is the power demand of the jth load, m is the total number of loads, is the power loss during the transmission process. represents the resistance of the transmission line, represents the power output of the kth generator.

9. The distributed energy scheduling optimization method according to claim 8, characterized in that: The specific calculation formula of the Pearson correlation coefficient is as follows: The specific calculation formula for the correlation between the frequency and the power generation is as follows: In the formula, is the Pearson correlation coefficient, is the number of data points, is the sum of the frequencies, is the sum of the power generation, is the sum of the product of frequency and power generation, is the sum of the squares of frequencies, is the sum of the squares of the power generation, is the frequency, is the frequency response coefficient of the system, is the amount of electricity generated.

10. The distributed energy scheduling optimization method according to claim 9, characterized in that: The frequency state and power dispatch impact data are used to obtain the grid stability coefficient based on the machine learning algorithm, as follows: The specific calculation formula of the power grid stability coefficient is as follows: In the formula, is the grid stability factor, is the electromagnetic torque, is the current grid frequency, It indicates the rated frequency of the power grid. is the power balance constraint state, It is the power loss during the transmission process.

Images