Inertia prediction method and device, storage medium and computer device

Abstract

The application relates to the technical field of power system optimization scheduling, and discloses an inertia prediction method and device, a storage medium and computer equipment, the method comprising the following steps: obtaining predicted inertia based on relevant influencing factors by using a preset inertia prediction model; constructing a day-ahead scheduling model according to a cost minimization principle, and establishing the day-ahead scheduling model and corresponding constraint conditions based on the predicted inertia; obtaining a day-ahead decision result corresponding to the day-ahead scheduling model, establishing an intra-day scheduling model and corresponding constraint conditions based on the day-ahead decision result and actual inertia; and constructing an inertia prediction target function and corresponding constraint conditions based on the day-ahead scheduling model and the intra-day scheduling model according to the cost minimization principle. The above method not only considers short-term economic benefits, but also takes into account long-term stability and sustainability, so that optimal allocation of resources is realized, the scheduling efficiency of a power system is improved, and the operation efficiency of the power system is improved by using accurate inertia prediction.

Description

Technical Field

[0001] This invention relates to the field of power system optimization scheduling technology, and in particular to an inertia prediction method, device, storage medium, and computer equipment. Background Technology

[0002] In traditional power systems, controllable power sources such as thermal and hydropower units dominate. These power sources possess strong load-tracking capabilities and regulation performance, effectively meeting the grid's inertia requirements and providing a solid foundation for the stable operation of the power system. However, with the large-scale integration of new energy power generation equipment, such as wind power and solar photovoltaic power, and the widespread application of power electronic converters, power systems are gradually shifting towards lower inertia. This shift has led to increased fluctuations in grid inertia levels, posing new challenges to system operational stability. Against this backdrop, inertia prediction has become an indispensable part of ensuring grid stability. Accurate inertia prediction not only provides a basis for daily power generation dispatch but also effectively guides the rational allocation of reserve resources, ancillary services, and emergency plans. This helps balance the power system's supply and demand, mitigates frequency fluctuations caused by insufficient inertia, and thus enhances the entire grid's resilience to emergencies, ensuring the security and reliability of power supply.

[0003] In existing technologies, inertia prediction and power grid optimization are often independent of each other because their goals are not entirely consistent. Traditional inertia prediction is usually based on a basic assumption that more accurate statistical prediction can lead to better decision-making. However, the impact of prediction errors on decision-making objectives may be asymmetric, non-monotonic, or even nonlinear. This means that simply pursuing more accurate predictions may not necessarily translate into better economic or operational results.

[0004] Therefore, an inertia prediction method that can lead to better decision-making results for power system operation, taking into account costs and other key factors, urgently needs to be studied. Summary of the Invention

[0005] In view of this, this application provides an inertia prediction method, apparatus, storage medium and computer equipment, the main purpose of which is to solve the technical problem that the inertia prediction of power systems in the prior art does not take cost factors into account and cannot bring better economic results.

[0006] According to a first aspect of the present invention, an inertia prediction method is provided.

[0007] Using a pre-defined inertia prediction model, the predicted inertia is obtained based on relevant influencing factors;

[0008] Based on the principle of cost minimization, a day-ahead scheduling model is constructed, and the first constraint condition corresponding to the day-ahead scheduling model is established based on the predicted inertia.

[0009] Obtain the day-ahead decision result corresponding to the day-ahead scheduling model, and establish an intraday scheduling model and the second constraint condition corresponding to the intraday scheduling model based on the day-ahead decision result and the actual inertia.

[0010] Based on the principle of cost minimization, an objective function for inertia prediction and a third constraint condition corresponding to the objective function are constructed based on the day-ahead scheduling model and the intraday scheduling model.

[0011] Optionally, the inertia prediction model is:

[0012]

[0013] In the formula: θ represents the predicted inertia; s represents the set of all scenes; Z represents the input feature vector; and θ represents the vector composed of the mapping coefficients of the relevant features.

[0014] Optionally, the day-ahead scheduling model is:

[0015]

[0016] The first constraint is:

[0017]

[0018]

[0019] In the formula: C() represents the system cost; To enable rapid response to unit action decisions; For predicting inertia; c1 is the unit reserve cost of the fast-response units in the system; c2 is the unit reserve cost of the slow-response units in the system; R1 is the reserve amount of the fast-response units in the system; R2 is the reserve amount of the slow-response units in the system; DA is the day-ahead phase; Forecasted reserve demand; T d Δf1 is the complete delivery time of a single frequency modulation response; ΔP is the maximum permissible frequency deviation; Δf1 is the maximum permissible frequency deviation. L 2 The power change rate is denoted as .

[0020] Optionally, the intraday scheduling model is:

[0021]

[0022] The second constraint is:

[0023]

[0024]

[0025] In the formula: RE represents the intraday real-time phase; R sys For the system's actual daily reserve requirements; H sys This is the actual inertia. For slow-response unit action decisions.

[0026] Optionally, the objective function is:

[0027]

[0028] The third constraint is:

[0029]

[0030] In the formula: 1,s represents the fast response units under all scenario sets; 2,s represents the slow response units under all scenario sets.

[0031] Optionally, the mean absolute percentage error of the objective function in prediction is:

[0032]

[0033] Optionally, the cost minimization principle is the principle of minimizing the actual operating cost of the power system, which includes the unit start-up and shutdown costs involved in day-ahead dispatching and intraday dispatching.

[0034] According to a second aspect of the present invention, an inertia prediction device is provided, the device comprising:

[0035] The predicted inertia acquisition model module is used to acquire predicted inertia based on relevant influencing factors using a preset inertia prediction model.

[0036] The day-ahead scheduling model building module is used to construct a day-ahead scheduling model based on the principle of cost minimization, and to establish the first constraint condition corresponding to the day-ahead scheduling model based on the predicted inertia.

[0037] The intraday scheduling model establishment module is used to obtain the day-ahead decision result corresponding to the day-ahead scheduling model, and establish the intraday scheduling model and the second constraint condition corresponding to the intraday scheduling model based on the day-ahead decision result and the actual inertia.

[0038] The inertia prediction objective function construction module is used to construct the objective function for inertia prediction and the corresponding third constraint condition based on the day-ahead scheduling model and the intraday scheduling model according to the cost minimization principle.

[0039] According to a third aspect of the present invention, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described inertia prediction method.

[0040] According to a fourth aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described inertia prediction method.

[0041] This invention provides an inertia prediction method, device, storage medium, and computer equipment. Utilizing a pre-defined inertia prediction model and based on relevant influencing factors, it obtains predicted inertia. Firstly, it accurately predicts the operating state of the power system within a future timeframe, facilitating advance planning and adjustment of grid operation strategies and reducing risks arising from uncertainty. Secondly, based on the principle of cost minimization, a day-ahead scheduling model is constructed, and a first constraint condition is established using the predicted inertia, resulting in more rational and efficient resource allocation and reduced overall operating costs. Thirdly, an intraday scheduling model is established based on day-ahead decision results and actual inertia, further refining real-time operation strategies, enhancing scheduling flexibility and adaptability, and ensuring rapid response to fluctuations in actual operation, thus improving the overall system's response speed and stability. This method not only considers short-term economic benefits but also long-term stability and sustainability, achieving optimal resource allocation. By utilizing accurate inertia prediction, it can better coordinate the relationships between different power sources, improving the scheduling efficiency and overall operating efficiency of the power system.

[0042] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0043] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0044] Figure 1 A flowchart illustrating an inertia prediction method provided by an embodiment of the present invention is shown.

[0045] Figure 2 A comparison chart of inertia prediction results under three different scenarios provided by embodiments of the present invention is shown.

[0046] Figure 3 A schematic diagram of the structure of an inertia prediction device provided in an embodiment of the present invention is shown;

[0047] Figure 4 A schematic diagram of the device structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0048] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0049] This application provides an inertia prediction method, such as... Figure 1 As shown, the method includes the following steps:

[0050] 101. Using a pre-defined inertia prediction model, obtain the predicted inertia based on relevant influencing factors.

[0051] The preset inertia prediction model is a pre-built mathematical or statistical model designed to simulate and predict inertia changes in power systems. The model specifically combines machine learning algorithms, physical models, or other data analysis techniques to understand and predict system behavior. Inertia changes are affected by various factors, including fluctuations in renewable energy, changes in load demand, and the output of traditional power generation facilities. By identifying and integrating these influencing factors, system inertia can be predicted more accurately. Based on the above model and the relevant input influencing factors, the predicted value of system inertia for a certain period of time in the future is obtained, providing basic data support for subsequent scheduling decisions.

[0052] In this embodiment, accurate inertia prediction allows for advance understanding of the power system's operating status, thereby enabling better planning and adjustment of the power grid's operating strategy and reducing risks caused by uncertainties, such as stability issues due to frequency deviations. Accurate inertia prediction helps maintain the frequency stability of the power system, which is crucial for ensuring the quality of power supply. Resource allocation based on prediction results can make energy utilization more efficient, reduce unnecessary reserve capacity, lower costs, and better coordinate the balance between traditional and renewable energy sources.

[0053] 102. Based on the principle of cost minimization, construct a day-ahead scheduling model and establish the first constraint condition corresponding to the day-ahead scheduling model based on the predicted inertia.

[0054] Cost minimization refers to reducing total operating costs as much as possible while meeting all necessary operational requirements. This may include fuel costs, maintenance costs, start-up / shutdown costs, etc. Day-ahead scheduling is a model used to plan the use of power generation resources over a period of 24 hours or longer. The model considers factors such as predicted load demand, market prices, and the availability of power generation resources. Day-ahead scheduling predicts future inertia to reflect changes in the dynamic characteristics of the system. The first constraint is a restriction set based on the predicted inertia to ensure that the scheduling plan not only minimizes costs but also maintains the stability and security of the system.

[0055] In this embodiment, by constructing a day-ahead scheduling model using the principle of cost minimization, the overall operating cost can be effectively reduced and economic efficiency improved. Combined with the first constraint condition set by the predicted inertia, the safe and stable operation of the system can be maintained even under inertia fluctuations. The scheduling strategy formulated based on accurate prediction data is more scientific and reasonable, reducing decision-making errors caused by insufficient or inaccurate information.

[0056] 103. Obtain the day-ahead decision results corresponding to the day-ahead scheduling model, and establish the intraday scheduling model and the second constraint conditions corresponding to the intraday scheduling model based on the day-ahead decision results and the actual inertia.

[0057] Among them, the day-ahead decision result is the optimal power generation plan calculated by the day-ahead scheduling model, including the start-up and shutdown time, output level, and other relevant operating parameters of each generator; the actual inertia refers to the system inertia value measured during actual operation. Unlike the predicted inertia, the actual inertia reflects the dynamic characteristics of the current system and may be affected by various factors; the intraday scheduling model is used to adjust the power generation plan according to the latest situation during the actual operation of the day. It combines the day-ahead decision result and the actual inertia, that is, it combines the pre-planned basis and real-time feedback information to ensure that the scheduling plan can adapt to real-time changes; the second constraint is the restriction condition set based on the day-ahead decision result and the actual inertia, which is used to ensure that the intraday scheduling model can be optimized under the premise of meeting the safety and stability requirements.

[0058] In this embodiment, the introduction of the intraday scheduling model enables the power grid to react quickly to real-time fluctuations, exhibiting strong flexibility and significantly enhancing its ability to cope with uncertainties. The second constraint condition based on actual inertia better reflects the dynamic characteristics of the current system, ensuring that the scheduling plan is not only economical and reasonable but also meets the system's safe operation requirements, helping to prevent frequency deviations and other potential problems. While day-ahead scheduling provides a macro-level plan, intraday scheduling further refines the operational strategy, comprehensively considering real-time information. The hierarchical management model makes resource allocation more precise and improves overall operational efficiency. By combining day-ahead decision results and actual inertia, the intraday scheduling model can effectively reduce the risks caused by prediction errors. Furthermore, the intraday scheduling model can flexibly adjust the proportion of renewable energy access based on changes in actual inertia, helping to better coordinate the relationship between traditional energy and renewable energy and improve the utilization rate of clean energy.

[0059] 104. Based on the principle of cost minimization, construct the objective function for inertia prediction and the corresponding third constraint condition based on the day-ahead scheduling model and the intraday scheduling model.

[0060] The objective function for inertia prediction is constructed to quantify the cost of system operation. This objective function considers not only traditional economic cost factors but also inertia prediction data from day-ahead and intraday scheduling models. The aim is to find an optimal operating scheme that guarantees both minimum cost and system inertia stability. The construction of the objective function requires comprehensive consideration of multiple variables, including generation costs, energy storage costs, load demand changes, renewable energy output fluctuations, and inertia changes. The third constraint is a series of restrictions established to ensure that the solution to the objective function meets practical operational requirements. Based on information provided by the day-ahead and intraday scheduling models, and considering the response speed and capacity of different power sources, generation tasks are rationally allocated to maintain the dynamic balance of the system.

[0061] In this embodiment, by constructing an objective function that comprehensively considers inertia prediction and applying the principle of cost minimization, economic benefits can be maximized while ensuring system safety and stability. This optimization method helps reduce overall operating costs and improve resource utilization. Setting a third constraint ensures that even with fluctuations in inertia levels, the system's frequency stability and other key performance indicators can be maintained. Combining day-ahead and intraday scheduling models with inertia prediction, the relationship between traditional and renewable energy sources can be coordinated more effectively. This not only better absorbs intermittent renewable energy but also reduces its negative impact on grid stability. The multi-level optimization framework enables the power system to quickly adjust its strategies in the face of constantly changing operating environments, enhancing the system's adaptability and flexibility.

[0062] This invention provides an inertia prediction method, device, storage medium, and computer equipment. Utilizing a pre-defined inertia prediction model and based on relevant influencing factors, it obtains predicted inertia. Firstly, it accurately predicts the operating state of the power system within a future timeframe, facilitating advance planning and adjustment of grid operation strategies and reducing risks arising from uncertainty. Secondly, based on the principle of cost minimization, a day-ahead scheduling model is constructed, and a first constraint condition is established using the predicted inertia, resulting in more rational and efficient resource allocation and reduced overall operating costs. Thirdly, an intraday scheduling model is established based on day-ahead decision results and actual inertia, further refining real-time operation strategies, enhancing scheduling flexibility and adaptability, and ensuring rapid response to fluctuations in actual operation, thus improving the overall system's response speed and stability. This method not only considers short-term economic benefits but also long-term stability and sustainability, achieving optimal resource allocation. By utilizing accurate inertia prediction, it can better coordinate the relationships between different power sources, improving the scheduling efficiency and overall operating efficiency of the power system.

[0063] In one implementation, the inertia prediction model is as follows:

[0064]

[0065] In the formula: θ represents the predicted inertia; s represents the set of all scenes; Z represents the input feature vector; and θ represents the vector composed of the mapping coefficients of the relevant features.

[0066] Specifically, in the day-ahead phase, it is usually necessary to predict the inertia level. The system's inertia level is not only affected by the system's operating mode, but also depends on changes in meteorological factors such as wind speed, sunlight, and temperature. The inertia is predicted based on the relevant influencing factors, and the results are used as input parameters to optimize system operation.

[0067] In one implementation, the day-ahead scheduling model is as follows:

[0068]

[0069] The first constraint is:

[0070]

[0071]

[0072] In the formula: C() represents the system cost; To enable rapid response to unit action decisions; For predicting inertia; c1 is the unit reserve cost of the fast-response units in the system; c2 is the unit reserve cost of the slow-response units in the system; R1 is the reserve amount of the fast-response units in the system; R2 is the reserve amount of the slow-response units in the system; DA is the day-ahead phase; Forecasted reserve demand; T d Δf1 is the complete delivery time of a single frequency modulation response; ΔP is the maximum permissible frequency deviation; Δf1 is the maximum permissible frequency deviation. L 2 The power change rate is denoted as .

[0073] In one implementation, the intraday scheduling model is as follows:

[0074]

[0075] The second constraint is:

[0076]

[0077]

[0078] In the formula: RE represents the intraday real-time phase; R sys For the system's actual daily reserve requirements; H sys This is the actual inertia. For slow-response unit action decisions.

[0079] In one implementation, the objective function is:

[0080]

[0081] The third constraint is:

[0082]

[0083] In the formula: 1,s represents the fast response units under all scenario sets; 2,s represents the slow response units under all scenario sets.

[0084] In one implementation, the mean absolute percentage error of the objective function prediction is:

[0085]

[0086] In one implementation, the cost minimization principle is the principle of minimizing the actual operating cost of the power system, which includes the unit start-up and shutdown costs involved in day-ahead and intraday dispatching.

[0087] Specifically, in one embodiment of the inertia prediction method provided in this application, four low-cost slow-speed CCGT (Combined Cycle Gas Turbine) units are first set up, each with a regulating reserve capacity of 60MW and a reserve cost of 50 yuan / MW; and nine high-cost fast-speed OCGT (Open Cycle Gas Turbine) units are set up, each with a regulating reserve capacity of 20MW and a reserve cost of 200 yuan / MW. The system parameters are set as follows: maximum power loss of 1800MW, primary frequency regulation response time of 10s, and maximum permissible frequency deviation of 0.8Hz. The specific training scenario is a dataset of 312 real meteorological and inertia data sets from a certain region, such as... Figure 2 The figure shows a comparison of inertia prediction results in three scenarios: Scenario 1, actual inertia under ideal conditions; Scenario 2, cost-oriented prediction method provided in this application; and Scenario 3, unit decision-making results based on inertia prediction values ​​obtained from BP neural network (BP Neural Network Prediction). The horizontal axis represents time (Hours), and the vertical axis represents inertia. The unit operating cost and inertia prediction MAPE under the three experimental scenarios are shown in the table below.

[0088]

[0089] Furthermore, as Figure 1 To specifically implement the method, this application provides an inertia prediction device, such as... Figure 3 As shown, the device includes: a predicted inertia acquisition model module 201, a day-ahead scheduling model establishment module 202, an intraday scheduling model establishment module 203, and an inertia prediction objective function construction module 204.

[0090] The predicted inertia acquisition model module 201 is used to acquire the predicted inertia based on relevant influencing factors using a preset inertia prediction model.

[0091] The day-ahead scheduling model building module 202 is used to build a day-ahead scheduling model according to the principle of cost minimization, and to establish the first constraint condition corresponding to the day-ahead scheduling model based on the predicted inertia.

[0092] Intraday scheduling model establishment module 203 is used to obtain the daytime decision results corresponding to the daytime scheduling model, and establish the intraday scheduling model and the second constraint conditions corresponding to the intraday scheduling model based on the daytime decision results and actual inertia.

[0093] The inertia prediction objective function construction module 204 is used to construct the objective function for inertia prediction and the corresponding third constraint condition based on the day-ahead scheduling model and the intraday scheduling model according to the cost minimization principle.

[0094] In specific application scenarios, the inertia prediction model in the inertia acquisition model module 201 is as follows:

[0095]

[0096] In the formula: θ represents the predicted inertia; s represents the set of all scenes; Z represents the input feature vector; and θ represents the vector composed of the mapping coefficients of the relevant features.

[0097] In a specific application scenario, the day-ahead scheduling model in module 202 is as follows:

[0098]

[0099] The first constraint is:

[0100]

[0101]

[0102] In the formula: C() represents the system cost; To enable rapid response to unit action decisions; For predicting inertia; c1 is the unit reserve cost of the fast-response units in the system; c2 is the unit reserve cost of the slow-response units in the system; R1 is the reserve amount of the fast-response units in the system; R2 is the reserve amount of the slow-response units in the system; DA is the day-ahead phase; Forecasted reserve demand; T d Δf1 is the complete delivery time of a single frequency modulation response; ΔP is the maximum permissible frequency deviation; Δf1 is the maximum permissible frequency deviation. L 2 The power change rate is denoted as .

[0103] In specific application scenarios, the intraday scheduling model in module 203 is as follows:

[0104]

[0105] The second constraint is:

[0106]

[0107]

[0108] In the formula: RE represents the intraday real-time phase; R sys For the system's actual daily reserve requirements; Hsys This is the actual inertia. For slow-response unit action decisions.

[0109] In a specific application scenario, the objective function in the inertia prediction objective function construction module 204 is:

[0110]

[0111] The third constraint is:

[0112]

[0113] In the formula: 1,s represents the fast response units under all scenario sets; 2,s represents the slow response units under all scenario sets.

[0114] In specific application scenarios, the average absolute percentage error of the objective function prediction in the inertia prediction objective function construction module 204 is:

[0115]

[0116] In specific application scenarios, the cost minimization principle in the inertia prediction objective function construction module 204 is the principle of minimizing the actual operating cost of the power system. The actual operating cost includes the unit start-up and shutdown costs involved in the day-ahead scheduling process and the intraday scheduling process.

[0117] It should be noted that other corresponding descriptions of the functional units involved in the inertia prediction device provided in this embodiment can be found in [reference needed]. Figure 1 The corresponding description in [the document] will not be repeated here.

[0118] Based on the above, Figure 1 Accordingly, this embodiment also provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-described inertia prediction method.

[0119] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product to be identified can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), including several instructions to enable a computer device (such as a personal computer, server, or network device) to execute the inertia prediction method for each implementation scenario of this application.

[0120] Based on the above, Figure 1 The method shown, and Figure 3 The inertia prediction device embodiment shown is designed to achieve the above objectives, such as... Figure 4As shown, this embodiment also provides a physical device for inertia prediction. This device includes a communication bus, a processor, a memory, and a communication interface. It may also include input / output interfaces and a display device. The various functional units can communicate with each other via the bus. The memory stores a computer program, and the processor executes the program stored in the memory to perform the inertia prediction method described in the above embodiment.

[0121] Optionally, the physical device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0122] Those skilled in the art will understand that the inertia prediction physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0123] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs to be identified. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0124] Through the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented through hardware. By applying the technical solution of this application, utilizing a preset inertia prediction model, and obtaining predicted inertia based on relevant influencing factors, the operating state of the power system in a certain period of time in the future can be accurately predicted. This helps to plan and adjust the power grid's operating strategy in advance and reduce the risks caused by uncertainty. On this basis, a day-ahead scheduling model is constructed according to the principle of cost minimization, and a first constraint condition is established in conjunction with the predicted inertia, making resource allocation more reasonable and efficient, reducing overall operating costs. Based on the day-ahead decision results and actual inertia, an intraday scheduling model is established, further refining the real-time operation strategy, enhancing the flexibility and adaptability of scheduling, ensuring a rapid response to fluctuations in actual operation, and improving the response speed and stability of the entire system. The above method not only considers short-term economic benefits but also takes into account long-term stability and sustainability, thereby achieving optimal resource allocation. By utilizing accurate inertia prediction, the relationship between different power sources can be better coordinated, improving the scheduling efficiency and operating efficiency of the power system.

[0125] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0126] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. An inertia prediction method, characterized in that, The method includes: Using a pre-defined inertia prediction model, the predicted inertia is obtained based on relevant influencing factors, among which... The inertia prediction model is as follows: sys = In the formula: sys For predicted inertia; s is the set of all scenes; Z is the input feature vector; A vector consisting of the mapping coefficients of the relevant features; Based on the principle of cost minimization, a day-ahead scheduling model is constructed, and a first constraint condition corresponding to the day-ahead scheduling model is established based on the predicted inertia. The day-ahead scheduling model is as follows: minC( 1)= + The first constraint is: ( 1， sys )： In the formula: C() represents the system cost; 1 is for fast-response unit action decision-making; sys To predict inertia; The unit reserve cost for fast-response units in the system; The unit reserve cost for slow-response units in the system; This is the reserve capacity for fast-response units in the system; This represents the reserve capacity of slow-response units in the system; DA represents the day-ahead phase. Forecasted reserve demand; The complete delivery time for a single frequency modulation response; This is the maximum permissible deviation of the frequency. The rate of change of power; Obtain the day-ahead decision result corresponding to the day-ahead scheduling model, and establish an intraday scheduling model and a second constraint condition corresponding to the intraday scheduling model based on the day-ahead decision result and the actual inertia, wherein the intraday scheduling model is: minC( 2)= The second constraint is: ( 1， 2， sys )： In the formula: RE This refers to the intraday real-time phase; This represents the system's actual daily reserve requirements; This is the actual inertia.

2. Action decision-making for slow-response units; Based on the principle of cost minimization, an objective function for inertia prediction and a third constraint condition corresponding to the objective function are constructed based on the day-ahead scheduling model and the intraday scheduling model.

2. The method according to claim 1, characterized in that, The objective function is: The third constraint is: ( 1， sys ) ( 1， 2， sys ) In the formula: 1,s represents the fast response units under all scenario sets; 2,s represents the slow response units under all scenario sets.

3. The method according to claim 1, characterized in that, The mean absolute percentage error of the prediction using the objective function is:

4. The method according to claim 1, characterized in that, The cost minimization principle refers to the principle of minimizing the actual operating cost of the power system, which includes the unit start-up and shutdown costs involved in day-ahead and intraday dispatching.

5. An inertia prediction device, characterized in that, The device includes: The predicted inertia acquisition model module is used to obtain the predicted inertia based on relevant influencing factors using a preset inertia prediction model. The inertia prediction model is as follows: sys = In the formula: sys For predicted inertia; s is the set of all scenes; Z is the input feature vector; A vector consisting of the mapping coefficients of the relevant features; The day-ahead scheduling model building module is used to construct a day-ahead scheduling model based on the cost minimization principle, and to establish the first constraint condition corresponding to the day-ahead scheduling model based on the predicted inertia, wherein the day-ahead scheduling model is: minC( 1)= + The first constraint is: ( 1， sys )： In the formula: C() represents the system cost; 1 is for fast-response unit action decision-making; sys To predict inertia; The unit reserve cost for fast-response units in the system; The unit reserve cost for slow-response units in the system; This is the reserve capacity for fast-response units in the system; This represents the reserve capacity of slow-response units in the system; DA represents the day-ahead phase. Forecasted reserve demand; The complete delivery time for a single frequency modulation response; This is the maximum permissible deviation of the frequency. The rate of change of power; The intraday scheduling model establishment module is used to obtain the day-ahead decision results corresponding to the day-ahead scheduling model, and establish an intraday scheduling model and a second constraint condition corresponding to the intraday scheduling model based on the day-ahead decision results and the actual inertia. The intraday scheduling model is as follows: minC( 2)= The second constraint is: ( 1， 2， sys )： In the formula: RE This refers to the intraday real-time phase; This represents the system's actual daily reserve requirements; This is the actual inertia.

2. Action decision-making for slow-response units; The inertia prediction objective function construction module is used to construct the objective function for inertia prediction and the corresponding third constraint condition based on the day-ahead scheduling model and the intraday scheduling model according to the cost minimization principle.

6. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images