A method and device for checking power flow at key sections of power grid
By constructing a key section power flow calculation intelligent agent based on BP neural network, the problem of long and inefficient power flow verification calculation process at key sections of the power grid is solved. It realizes direct calculation from the current power grid operating parameters to the next decision cycle, thereby improving the calculation efficiency and the safety and reliability of power grid operation.
Patent Information
- Application Number
- CN202111197264.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-14
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2041-10-14
AI Technical Summary
Existing power flow verification methods for critical sections of power grids have long calculation processes and low efficiency. In particular, it is difficult to balance calculation efficiency and accuracy when verifying online. Traditional methods have failed to achieve direct calculation from the current power grid operating parameters to the next decision cycle.
A key section power flow calculation agent based on a BP neural network is constructed. By selecting the operating status of power transmission and transformation equipment and the load of the unified dispatch as input signals, the agent is standardized and the parameters of the agent are optimized using the training dataset, so as to directly calculate the key section power flow in the next decision cycle.
It simplifies the calculation process, improves calculation efficiency, ensures the safety and reliability of power grid operation, and enables direct calculation from current power grid operating parameters to the next decision cycle.
Smart Images

Figure CN113872210B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power grid operation monitoring, and in particular to a real-time blocking adjustment method and device for a key section of a power grid. Background Art
[0002] The key section flow verification of large power grid is an important part of power grid dispatching operation analysis and safety control. The main verification method is to compare the section flow and flow limit to determine whether the key section flow exceeds the limit requirement.
[0003] The current verification method includes two core technologies. The first is to calculate the power flow limit of key sections. The power flow limit calculation needs to comprehensively consider the operation control requirements such as static stability and transient stability of the power grid, and conduct comprehensive calculation and analysis. The power flow limit calculation is generally carried out offline, that is, according to the typical operation mode of the power grid, the operation control requirements under different scenarios are calculated, and the power flow limit of key sections is comprehensively formulated. The second is to calculate the power flow of key sections. The power grid power flow calculation formula is essentially a highly nonlinear formula. When the Newton-Raphson method is used to solve the power flow, the forward regression method or the fast power flow decomposition calculation method is generally used. However, due to the highly nonlinear characteristics of the model itself, the amount of calculation is still large. If the verification results show that the power flow of the key section will exceed the power flow limit, it means that the operation mode of the power grid is not reasonably arranged, and it is necessary to adjust the power generation plan, the unit start-up and shutdown plan and other measures to adjust the section power flow to meet the safety needs of the power grid.
[0004] Therefore, the implementation process of the traditional cross-section power flow verification method can be divided into four key steps: cross-section power flow limit calculation, power flow calculation boundary data preparation, power flow calculation, and over-limit verification. Cross-section power flow limit calculation is the process of calculating the cross-section power flow limit based on power grid analysis such as static stability and transient stability. The preparation of power flow calculation boundary data includes load forecasting, new energy forecasting, etc., which serve as the basic data for power flow calculation. Power flow calculation is the process of using the Newton-Raphson method to calculate and analyze the power grid power flow during the verification period. Over-limit verification is the process of comparing cross-section power flow and cross-section power flow limit. However, when the above key cross-section power flow verification method is used to solve the online verification problem, it will face the prominent problems of long calculation process and low calculation efficiency. Since the cross-section power flow limit calculation can be obtained in advance by offline method, the boundary data preparation and cross-section power flow calculation are the prominent links that cause the above problems. First, the boundary data preparation and cross-section power flow calculation involve two links, and the execution efficiency is low. During the online verification period, load forecasts and new energy forecasts are mainly obtained based on data analysis based on the current operating status. The cross-sectional flow calculation is performed based on the forecast information for the next decision cycle. There is no direct measurement method from the current status to the cross-sectional flow, and the process is relatively long. Second, there are inherent difficulties between the calculation efficiency and calculation accuracy of the cross-sectional flow calculation. The forward-backward method and the fast decomposition method are the two main solution methods for solving the power grid flow calculation under the Newton-Raphson method. The forward-backward method requires repeated iterations, and the solution efficiency is low but the accuracy is relatively high. The fast decomposition method improves the calculation efficiency by decomposing the active and reactive characteristics. It is efficient but has inherent calculation errors. Summary of the invention
[0005] The embodiment of the present invention provides a method and device for verifying the power flow of a key section of a power grid, constructs a key section power flow calculation intelligent entity based on a BP neural network, realizes the direct calculation of the key parameters of the current power grid operation to the key section power flow of the next decision cycle, simplifies the calculation process, and improves the calculation efficiency.
[0006] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a method for verifying power flow at a key section of a power grid, the method comprising:
[0007] Selecting the operating status and coordinated load of multiple power transmission and transformation equipment as input signals of the section power flow calculation intelligent body, and performing standardization processing on the input signals;
[0008] According to the actual needs of the power flow calculation, adjusting the parameters of the section power flow calculation intelligent agent to change the output signal type of the section power flow calculation intelligent agent;
[0009] Inputting the input signal after the standardization process into the trained section power flow calculation agent, and obtaining the key section power flow of the next decision cycle from the output signal of the trained section power flow calculation agent;
[0010] If it is found through verification that the critical section flow is greater than the preset section limit, the multiple power transmission and transformation equipment are adjusted according to the power transmission and transformation equipment adjustment amount in the output signal to obtain the critical section flow after adjustment in the next decision cycle.
[0011] In a possible implementation of the first aspect, the line disconnection distribution factor LODF values of the multiple power transmission and transformation equipment are all greater than the preset key section LODF value; the LODF value corresponding to the power transmission and transformation equipment reflects the impact on the section flow when the power transmission and transformation equipment is disconnected.
[0012] In a possible implementation manner of the first aspect, selecting the operating states and coordinated loads of multiple power transmission and transformation equipment as input signals of the section power flow calculation intelligent agent specifically includes:
[0013] The unified dispatching load, planned power generation of key positively correlated units, planned power generation of key negatively correlated units, new energy power generation output and maintenance status of key transmission and transformation equipment are selected as input signals of the section power flow calculation intelligent body.
[0014] In a possible implementation manner of the first aspect, the centralized load is a current grid centralized load;
[0015] The control load is converted into a positive number between 0 and 1 by using the maximum and minimum value linear conversion method.
[0016] In a possible implementation of the first aspect, the planned power generation of the key positively correlated units is the sum of the planned power generation of the key positively correlated generating units; the key positively correlated units are the set of units whose power generation power transfer distribution factor GSDF value is greater than the transfer threshold among the positively correlated units; the positively correlated units refer to generating units whose power generation output is positively correlated with the section flow;
[0017] The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key positively correlated units into a positive number between 0 and 1.
[0018] In a possible implementation of the first aspect, the planned power generation of the key negatively correlated units is the sum of the planned power generation of the key negatively correlated generating units; the key negatively correlated units are the set of units whose power generation power transfer distribution factor GSDF value is less than the transfer threshold among the negatively correlated units; the negatively correlated units are generating units whose power generation output is negatively correlated with the section flow;
[0019] The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key negatively correlated units into a positive number between 0 and 1.
[0020] In a possible implementation of the first aspect, the renewable energy power generation output is the sum of the power generation outputs of the current renewable energy power stations in the entire network, and the renewable energy power generation output is converted into a positive number between 0 and 1 using a maximum and minimum value linear conversion method.
[0021] In a possible implementation manner of the first aspect, before inputting the standardized input signal into the trained section power flow calculation agent, the method further includes:
[0022] A training data set of the cross-section power flow calculation intelligent agent is constructed by combining historical data with an optimal control method;
[0023] The section flow calculation intelligent agent is trained using the training data set.
[0024] In a possible implementation of the first aspect, the output signal of the section flow calculation intelligent agent includes the critical section flow, the adjusted critical section flow, the power generation output adjustment of the key positively correlated unit, the power generation output adjustment of the key negatively correlated unit and the new energy output adjustment.
[0025] A second aspect of the embodiment of the present application provides a power grid key section power flow verification device, including:
[0026] An input module is used to select the operating status of multiple power transmission and transformation equipment and the centralized load as input signals of the section power flow calculation intelligent body, and perform standardization processing on the input signals;
[0027] A parameter adjustment module, used to adjust the parameters of the section power flow calculation intelligent agent to change the output signal type of the section power flow calculation intelligent agent according to the actual needs of the power flow calculation;
[0028] An output module, used for inputting the input signal after the standardization process into the trained section power flow calculation agent, and obtaining the key section power flow of the next decision cycle from the output signal of the trained section power flow calculation agent;
[0029] The equipment adjustment module is used to adjust the multiple power transmission and transformation equipment according to the power transmission and transformation equipment adjustment amount in the output signal and obtain the adjusted key section flow in the next decision cycle if it is found through verification that the key section flow is greater than the preset section limit.
[0030] Compared with the prior art, the key section power flow verification method and device provided in the embodiment of the present invention construct a key section power flow calculation intelligent entity based on the BP neural network, realizes the direct calculation of the key section power flow from the current key parameters of the power grid operation to the next decision cycle, and uses the section power flow limit calculated in an offline manner to implement online verification, which simplifies the calculation process and improves the calculation efficiency.
[0031] Specifically, the input signal and output signal of the key section flow calculation intelligent agent are determined according to the needs of the key section flow verification of the power grid, and the relevant parameters of the key section flow calculation intelligent agent are adjusted accordingly and the data processing method of the input signal and the output signal is formulated. Then the key section flow calculation intelligent agent is trained using the training data set. The process of training the key section flow calculation intelligent agent is essentially a process of further optimizing and adjusting the intelligent agent parameters according to the difference between the output signal and the target signal. Finally, the key section flow calculation intelligent agent that meets the training requirements is used to verify the key section flow of the power grid and output the key section flow, the adjusted key section flow, the key positively correlated unit power generation output adjustment, the key negatively correlated unit power generation output adjustment and the new energy output adjustment. After the actual verification, the power transmission and transformation equipment is adjusted according to each adjustment amount to affect the key section flow, making the power grid operation safer and more reliable. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 It is a flow chart of a method for verifying power flow at a key section of a power grid provided in one embodiment of the present invention. DETAILED DESCRIPTION
[0033] 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.
[0034] See also Figure 1 An embodiment of the present invention provides a method for checking power flow at a key section of a power grid, the method comprising:
[0035] S10, selecting the operating status and coordinated load of multiple power transmission and transformation equipment as input signals of the section power flow calculation intelligent body, and performing standardization processing on the input signals.
[0036] S11. According to actual needs of power flow calculation, adjust the parameters of the section power flow calculation intelligent agent to change the output signal type of the section power flow calculation intelligent agent.
[0037] S12, inputting the input signal after the standardization process into the trained section power flow calculation agent, and obtaining the key section power flow of the next decision cycle from the output signal of the trained section power flow calculation agent.
[0038] S13. If it is found through verification that the critical section power flow is greater than the preset section limit, the multiple power transmission and transformation equipment are adjusted according to the power transmission and transformation equipment adjustment amount in the output signal to obtain the critical section power flow after adjustment in the next decision cycle.
[0039] S10-S11 is an important stage in the intelligent agent construction phase, and the purpose of S10 is to determine the input signal of the section flow calculation intelligent agent based on BP neural network according to the actual needs of flow calculation in the online verification problem of key section flow of large power grid, and perform data processing on it.
[0040] The purpose of S11 is to determine the output signal of the section flow calculation intelligent agent based on BP neural network according to the actual needs of flow calculation in the online verification problem of key section flow of large power grid, and perform data processing on it.
[0041] S12-S13 belongs to the application stage of the cross-section flow calculation intelligent agent, which applies the intelligent agent that meets the training requirements to the actual key cross-section flow online verification problem.
[0042] According to the basic theory of power dispatching and operation, the key section flow is affected by factors such as load level, load distribution, startup mode, power generation output, and maintenance mode of power transmission and transformation equipment. In theory, if the operating status of all power transmission and transformation equipment in the power grid is used as the input signal, the accuracy of the intelligent agent's decision can be maximized. However, when the input signal dimension exceeds a certain limit, the training efficiency of the intelligent agent for section flow calculation will drop significantly, and the operating status of a large number of power transmission and transformation equipment is not closely related to the key section flow, which will lead to a lot of interference in the input signal, which will lead to a decrease in the accuracy of the intelligent agent's decision. To this end, the input signal must be accurately selected. In order to accurately select the input signal, it is very necessary to accurately select the relevant power transmission and transformation equipment with a large impact.
[0043] Exemplarily, the line disconnection distribution factor LODF values of the multiple power transmission and transformation equipment are all greater than the preset key section LODF value; the LODF value corresponding to the power transmission and transformation equipment reflects the impact on the section flow when the power transmission and transformation equipment is disconnected.
[0044] Critical power transmission and transformation equipment refers to a set of power transmission and transformation equipment whose operating status has a significant impact on the power flow distribution of critical sections. Line off distribution factor (LODF) is used to determine critical power transmission equipment. LODF reflects the impact of a certain line on the power flow of other lines or sections when it is disconnected. Its numerical value reflects the degree of power flow transfer, and the numerical symbol indicates the direction of power flow transfer. Determine the LODF limit of the critical power transmission and transformation equipment of the critical section. If the LODF value of a certain power transmission and transformation equipment and the critical section exceeds the limit, it indicates that the power transmission and transformation equipment is the critical power transmission and transformation equipment of the critical section, otherwise it does not belong to the critical power transmission and transformation equipment. The limit needs to be determined based on a comprehensive analysis of the actual operating characteristics of the power grid. It can generally be set to 0.5, that is, before and after the power transmission and transformation equipment is disconnected, the power flow of the critical section will correspond to a change of more than half of the power flow value of the power transmission and transformation equipment, then the power transmission and transformation equipment is the critical power transmission and transformation equipment of the critical section.
[0045] Exemplarily, the selecting the operating status of multiple power transmission and transformation equipment and the coordinated load as the input signal of the section power flow calculation intelligent agent specifically includes:
[0046] The unified dispatching load, planned power generation of key positively correlated units, planned power generation of key negatively correlated units, new energy power generation output and maintenance status of key transmission and transformation equipment are selected as input signals of the section power flow calculation intelligent body.
[0047] Exemplarily, the centralized load is the current power grid centralized load; the centralized load is converted into a positive number between 0 and 1 using a maximum and minimum value linear conversion method.
[0048] The coordinated load is the current grid coordinated load. Considering the large range of data variation, in order to improve the training efficiency, the maximum and minimum linear transformation method is used to transform it into a positive number between [0, 1], where the maximum and minimum values are the maximum and minimum values of the coordinated load prediction within the decision cycle, respectively.
[0049] Exemplarily, the planned power generation of the key positively correlated units is the sum of the planned power generation of the key positively correlated generating units; the key positively correlated units are the set of units whose power generation transfer distribution factor GSDF value is greater than the transfer threshold among the positively correlated units; the positively correlated units refer to generating units whose power generation output is positively correlated with the section flow;
[0050] The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key positively correlated units into a positive number between 0 and 1.
[0051] In the operation of the power grid, a positively correlated unit refers to a generator unit whose power output is positively correlated with the section flow, and a key positively correlated unit is a set of units among the positively correlated units that have a significant impact on the key section flow. A negatively correlated unit refers to a generator unit whose power output is negatively correlated with the section flow, and a key negatively correlated unit is a set of units among the negatively correlated units that have a significant impact on the key section flow. The generation power transfer distribution factor (GSDF) can be used to determine the key positively correlated units and the key negatively correlated units. It is stipulated that the value of the power transfer distribution factor between the generator unit and the key section exceeds the limit value, which is a key-related unit, and the positive and negative signs of the power transfer distribution factor are used to distinguish between positive and negatively correlated units. The limit value needs to be determined according to the needs of different power grid operation characteristics, and can generally be selected as 0.7, that is, if the output of the generator unit changes by 1 unit, it will cause the key section flow to change by 0.7 units or more, which is a key-related unit.
[0052] The planned power generation of key positively correlated units is the sum of the planned power generation of key positively correlated generating units. Considering the large range of data variation, in order to improve the training efficiency, the maximum and minimum linear transformation method is used to transform it into a positive number between [0, 1], where the maximum and minimum values are the sum of the maximum and minimum technical planned outputs of key positively correlated generating units, respectively.
[0053] Exemplarily, the planned power generation of the key negatively correlated units is the sum of the planned power generation of the key negatively correlated generating units; the key negatively correlated units are the set of units whose power generation transfer distribution factor GSDF value is less than the transfer threshold among the negatively correlated units; the negatively correlated units refer to generating units whose power generation output is negatively correlated with the section flow.
[0054] The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key negatively correlated units into a positive number between 0 and 1.
[0055] The planned power generation of the key negatively correlated units is the sum of the planned power generation of the key negatively correlated generating units. Considering the large range of data variation, in order to improve the training efficiency, the maximum and minimum linear transformation method is used to convert it into a positive number between [0, 1], where the maximum and minimum values are the sum of the maximum and minimum technical planned outputs of the key negatively correlated generating units, respectively. Exemplarily, the new energy power generation output is the sum of the power generation outputs of the current new energy power stations in the entire network, and the maximum and minimum linear transformation method is used to convert the new energy power generation output into a positive number between 0 and 1.
[0056] The renewable energy power generation output is the sum of the current power generation outputs of renewable energy power stations in the entire network. Taking into account the large range of data variation, in order to improve the training efficiency, the maximum and minimum linear transformation method is used to transform it into a positive number between [0, 1], where the maximum and minimum values are the maximum and minimum values of the predicted installed capacity of the renewable energy power station, respectively.
[0057] For example, for the key power transmission and transformation set S={s1,s2,…s N}, where s1, s 2 、……s N are the key power transmission and transformation equipment sorted out according to the above method, and N is the number of key power transmission and transformation equipment. Since each power transmission and transformation equipment has two states: running and shut down, there are 2 values of the key power transmission and transformation set. N Cases. With positive integers 1, 2, ... 2 N The key transmission and transformation set values are numbered. Considering the large range of data variation, in order to improve the training efficiency, the maximum and minimum linear transformation method is used to transform them into positive numbers between [0, 1], where the maximum and minimum values are 2 N , 1.
[0058] Through the above input signal definition and data processing, the input signal can be expressed in the form of a set as in, After data processing, the current coordinated load and renewable energy power generation output are obtained. It is the power generation output of the key positively correlated units and the power generation output of the key negatively correlated units in the next decision cycle after data processing. It is a set of key power transmission and transformation equipment at the current moment and the next decision cycle after data processing.
[0059] It should be noted that The current coordinated load and renewable energy power generation output after data processing. These two indicators are the actual data at the current moment, which are also the basic data based on the prediction stage in the traditional verification method; The power output of the key positively correlated units and the power output of the key negatively correlated units in the next decision cycle after data processing. These two items have been determined by the power generation plan preparation business. Although they are the planning information for the next decision cycle, they have actually been determined a day or an hour in advance and are known information; It is the set of key power transmission and transformation equipment at the current moment and the next decision cycle after data processing. These two items have been determined by the power transmission and transformation equipment planning business. Although it is the planning information for the next decision cycle, it has actually been determined a day or an hour ago and is known information.
[0060] In actual applications, relevant staff can go a step further and classify data from the perspective of planning and prediction. New energy and load are not determined by dispatching and operating personnel, and can only be predicted in multiple time series. In the online verification problem, the traditional model needs to predict them based on the current actual load and new energy, and then verify whether the section exceeds the limit; planning information includes power outage and power restoration plans for power transmission and transformation equipment and conventional power generation plans, which are determined or arranged by dispatching and operating personnel. In the online verification, the above operation plans have been determined and belong to the boundary data of the verification. The traditional verification method will not predict them, but will also use them as the verification boundary. This embodiment uses prediction information and planning information as the boundaries of decision-making, and integrates traditional prediction, flow calculation, etc. into an intelligent decision-making process.
[0061] Exemplarily, before inputting the input signal after the standardization process into the trained section power flow calculation agent, the method further includes:
[0062] The training data set of the section flow calculation intelligent agent is constructed by combining historical data with the optimal control method.
[0063] The section flow calculation intelligent agent is trained using the training data set.
[0064] The main task of the agent training stage is to train the cross-section flow calculation agent using the training data set. The process of cross-section flow calculation agent training is essentially the process of optimizing and adjusting the agent parameters based on the difference between the output signal and the target signal. The training process belongs to the more mature algorithm flow of the BP neural network, so the focus of the actual application process is to determine the training data set.
[0065] Preferably, the agent training data set is constructed by combining historical data with the optimal control method. Collect at least 1 year of actual operation data, and use the flow calculation method based on the forward-backward method according to the historical data scenario under each online verification to obtain the key section flow of the next decision cycle; if the flow exceeds the limit, refer to the optimal control method, construct a decision model, and calculate the power generation plan of the key related units and the new energy power generation plan. Referring to the data processing method in the above embodiment, the data obtained in the above offline analysis process is converted into the neural network agent input signal and the ideal output signal Among them, power flow calculation and optimal control method are relatively mature technologies in the current field of power grid dispatching and operation. They do not affect the understanding of professional and technical personnel in this field, and their specific implementation processes are not repeated here.
[0066] Exemplarily, the output signal of the section flow calculation intelligent agent includes the key section flow, the adjusted key section flow, the key positively correlated unit power generation output adjustment, the key negatively correlated unit power generation output adjustment and the new energy output adjustment.
[0067] According to the actual needs of power grid dispatching and operation, the purpose of section flow calculation and online verification is not only to calculate the section flow and determine whether it is over-limit, but also to obtain suggestions on how to effectively eliminate the over-limit after the over-limit. To this end, the output signal in this embodiment includes five items: key section flow, adjusted key section flow, key positively correlated unit power output adjustment, key negatively correlated unit power output adjustment, and new energy output adjustment.
[0068] Since the input signal has been converted into data in the range [0,1] using the maximum and minimum linear conversion method, the output signal is also converted using the corresponding maximum and minimum values. The output signal can be expressed in a set form as in is the expected tidal current at the critical section. If it does not exceed the limit, the value is between -1 and 1. The symbol is the tidal current direction, and the value indicates the tidal current size. For the key section tidal current after taking control measures, the value should be between -1 and 1; They are adjustments made to the power generation plans of key positively correlated units, the power generation units of key negatively correlated units and the power generation output of new energy in order to regulate the current in key sections.
[0069] Compared with the prior art, the key section flow verification method of the power grid provided in the embodiment of the present invention constructs a key section flow calculation intelligent entity based on the BP neural network, realizes the direct calculation of the key section flow from the current key parameters of the power grid operation to the key section flow of the next decision cycle, and uses the section flow limit calculated in an offline manner to implement online verification, which simplifies the calculation process and improves the calculation efficiency.
[0070] Specifically, the input signal and output signal of the key section flow calculation intelligent agent are determined according to the needs of the key section flow verification of the power grid, and the relevant parameters of the key section flow calculation intelligent agent are adjusted accordingly and the data processing method of the input signal and the output signal is formulated. Then the key section flow calculation intelligent agent is trained using the training data set. The process of training the key section flow calculation intelligent agent is essentially a process of further optimizing and adjusting the intelligent agent parameters according to the difference between the output signal and the target signal. Finally, the key section flow calculation intelligent agent that meets the training requirements is used to verify the key section flow of the power grid and output the key section flow, the adjusted key section flow, the key positively correlated unit power generation output adjustment, the key negatively correlated unit power generation output adjustment and the new energy output adjustment. After the actual verification, the power transmission and transformation equipment is adjusted according to each adjustment amount to affect the key section flow, making the power grid operation safer and more reliable.
[0071] An embodiment of the present application provides a power grid key section power flow verification device, including an input module, a parameter adjustment module, an output module and an equipment adjustment module.
[0072] The input module is used to select the operating status and coordinated load of multiple power transmission and transformation equipment as input signals of the section power flow calculation intelligent body, and perform standardized processing on the input signals.
[0073] The parameter adjustment module is used to adjust the parameters of the section power flow calculation intelligent agent according to the actual needs of the power flow calculation to change the output signal type of the section power flow calculation intelligent agent.
[0074] The output module is used to input the input signal after standardization processing into the trained section power flow calculation agent, and obtain the key section power flow of the next decision cycle from the output signal of the trained section power flow calculation agent.
[0075] The equipment adjustment module is used to adjust the multiple power transmission and transformation equipment according to the power transmission and transformation equipment adjustment amount in the output signal and obtain the adjusted key section power flow in the next decision cycle if it is found through verification that the key section power flow is greater than the preset section limit.
[0076] Compared with the prior art, the key section flow verification device of the power grid provided in the embodiment of the present invention constructs a key section flow calculation intelligent entity based on the BP neural network, realizes the direct calculation of the key section flow from the current key parameters of the power grid operation to the key section flow of the next decision cycle, and uses the section flow limit calculated in an offline manner to implement online verification, which simplifies the calculation process and improves the calculation efficiency.
[0077] Specifically, the input signal and output signal of the key section flow calculation intelligent agent are determined according to the needs of the key section flow verification of the power grid, and the relevant parameters of the key section flow calculation intelligent agent are adjusted accordingly and the data processing method of the input signal and the output signal is formulated. Then the key section flow calculation intelligent agent is trained using the training data set. The process of training the key section flow calculation intelligent agent is essentially a process of further optimizing and adjusting the intelligent agent parameters according to the difference between the output signal and the target signal. Finally, the key section flow calculation intelligent agent that meets the training requirements is used to verify the key section flow of the power grid and output the key section flow, the adjusted key section flow, the key positively correlated unit power generation output adjustment, the key negatively correlated unit power generation output adjustment and the new energy output adjustment. After the actual verification, the power transmission and transformation equipment is adjusted according to each adjustment amount to reflect the key section flow, making the power grid operation safer and more reliable.
[0078] An embodiment of the present application provides a computer-readable storage medium, which includes a stored computer program; wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the method for checking power flow at a critical section of a power grid as described above.
[0079] Preferably, the computer program can be divided into one or more modules / units (such as computer program, computer program), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.
[0080] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the terminal device, and various parts of the terminal device are connected by various interfaces and lines.
[0081] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMed ia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory can also be other volatile solid-state storage devices.
[0082] It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above-mentioned terminal device is merely an example and does not constitute a limitation on the terminal device. It may include more or fewer components, or a combination of certain components, or different components.
[0083] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for checking power flow at key sections of a power grid. It is characterized in that include: The operating status and unified load of multiple power transmission and transformation equipment are selected as input signals of the section flow calculation intelligent body, and the input signals are standardized; wherein the input signals include unified load, planned power generation of key positively related units, planned power generation of key negatively related units, new energy power generation output and maintenance status of key power transmission and transformation equipment; the line disconnection distribution factor LODF values of the multiple power transmission and transformation equipment are all greater than the preset key section LODF value; the LODF value corresponding to the power transmission and transformation equipment reflects the impact on the section flow when the power transmission and transformation equipment is disconnected; According to the actual needs of the power flow calculation, adjusting the parameters of the section power flow calculation intelligent agent to change the output signal type of the section power flow calculation intelligent agent; The input signal after the standardization process is input into the trained section flow calculation intelligent agent, and the key section flow of the next decision cycle is obtained from the output signal of the trained section flow calculation intelligent agent; wherein the training process of the section flow calculation intelligent agent includes: constructing a training data set of the section flow calculation intelligent agent by combining historical data with an optimal control method; and training the section flow calculation intelligent agent by using the training data set; If it is found through verification that the critical section flow is greater than the preset section limit, the multiple power transmission and transformation equipment are adjusted according to the power transmission and transformation equipment adjustment amount in the output signal to obtain the critical section flow after adjustment in the next decision cycle.
2. The method for verifying power flow at a key section of a power grid according to claim 1, It is characterized in that The centralized load is the current power grid centralized load; The control load is converted into a positive number between 0 and 1 by using the maximum and minimum value linear conversion method.
3. The method for verifying power flow at a key section of a power grid according to claim 1, It is characterized in that The planned power generation of the key positively correlated units is the sum of the planned power generation of the key positively correlated generating units; the key positively correlated units are the set of units whose power generation transfer distribution factor GSDF value is greater than the transfer threshold among the positively correlated units; the positively correlated units refer to the generating units whose power generation output is positively correlated with the section flow; The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key positively correlated units into a positive number between 0 and 1.
4. The method for verifying power flow at a key section of a power grid according to claim 1, It is characterized in that The planned power generation of the key negatively correlated units is the sum of the planned power generation of the key negatively correlated generating units; the key negatively correlated units are the set of units whose power generation transfer distribution factor GSDF value is less than the transfer threshold among the negatively correlated units; the negatively correlated units refer to the generating units whose power generation output is negatively correlated with the section flow; The maximum and minimum value linear conversion method is adopted to convert the planned power generation of the key negatively correlated units into a positive number between 0 and 1.
5. The method for verifying power flow at a key section of a power grid according to claim 1, It is characterized in that The renewable energy power generation output is the sum of the power generation outputs of the renewable energy power stations in the entire network. The renewable energy power generation output is converted into a positive number between 0 and 1 using the maximum and minimum value linear conversion method.
6. The method for verifying power flow at a key section of a power grid according to claim 1, It is characterized in that The output signal of the section flow calculation intelligent body includes the key section flow, the adjusted key section flow, the key positively correlated unit power generation output adjustment, the key negatively correlated unit power generation output adjustment and the new energy output adjustment.
7. A power grid key section power flow verification device, It is characterized in that include: An input module is used to select the operating status of multiple power transmission and transformation equipment and the centralized load as input signals of the section flow calculation intelligent body, and standardize the input signals; wherein the input signals include the centralized load, the planned power generation of key positively related units, the planned power generation of key negatively related units, the power generation output of new energy, and the maintenance status of key power transmission and transformation equipment; the line disconnection distribution factor LODF values of the multiple power transmission and transformation equipment are all greater than the preset key section LODF value; the LODF value corresponding to the power transmission and transformation equipment reflects the impact on the section flow when the power transmission and transformation equipment is disconnected; A parameter adjustment module, used to adjust the parameters of the section power flow calculation intelligent agent to change the output signal type of the section power flow calculation intelligent agent according to the actual needs of the power flow calculation; The output module is used to input the input signal after the standardization process into the trained section flow calculation intelligent agent, and obtain the key section flow of the next decision cycle from the output signal of the trained section flow calculation intelligent agent; wherein the training process of the section flow calculation intelligent agent includes: constructing a training data set of the section flow calculation intelligent agent by combining historical data with the optimal control method; and training the section flow calculation intelligent agent by using the training data set; The equipment adjustment module is used to adjust the multiple power transmission and transformation equipment according to the power transmission and transformation equipment adjustment amount in the output signal and obtain the adjusted key section flow in the next decision cycle if it is found through verification that the key section flow is greater than the preset section limit.
