Power grid energy dispatching method, device, computer equipment and readable storage medium

Abstract

The present application relates to a method, device, computer equipment and readable storage medium for power grid energy dispatching. The method comprises: obtaining the operation data of the power grid, performing state estimation on a pre-constructed power grid diagram model according to the operation data, determining the operation state of the power grid, generating an initial energy dispatching scheme according to the operation state of the power grid, solving the comprehensive cost minimization objective function, obtaining the optimal solution of the function, optimizing and adjusting the initial energy dispatching scheme based on the optimal solution of the function, obtaining the adjusted target energy dispatching scheme, the comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operation time, unit carbon emissions, and carbon emission cost of the power station, and performing energy dispatching on the power grid based on the target energy dispatching scheme. The use of this method can effectively improve the energy dispatching efficiency of the power grid.

Description

Technical Field

[0001] The present application relates to the technical field of power grid dispatching, and in particular to a power grid energy dispatching method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Grid energy optimization and dispatch is an important part of power system operation and management, which aims to ensure the stable, reliable and economic operation of the power system by reasonably arranging the power generation of power stations and the transmission power of transmission lines. With the opening of the power market and the large-scale access of renewable energy, grid energy optimization and dispatch is facing more complex challenges, and traditional dispatch methods can no longer meet the needs of modern power grids.

[0003] The key parameters in the power system will change with time and external environment, making it difficult to accurately assess the impact of these parameter changes on the optimization plan, and the generated dispatch plan is fixed for a certain period of time. When the key parameters change, the system cannot adjust the optimization plan in time, resulting in low dispatch efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide an efficient power grid energy scheduling method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a power grid energy scheduling method, comprising:

[0006] Obtaining the operation data of the power grid;

[0007] Performing state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation state of the power grid;

[0008] generating an initial energy scheduling plan according to the operating status of the power grid;

[0009] Solving the comprehensive cost minimization objective function to obtain the optimal solution of the function, optimizing and adjusting the initial energy scheduling plan based on the optimal solution of the function to obtain an adjusted target energy scheduling plan, wherein the comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station;

[0010] Energy scheduling is performed on the power grid based on the target energy scheduling scheme.

[0011] In one embodiment, solving the comprehensive cost minimization objective function to obtain the optimal solution of the function, optimizing and adjusting the initial energy scheduling plan based on the optimal solution of the function to obtain the adjusted target energy scheduling plan, includes:

[0012] Obtain the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost of the power station;

[0013] Based on the unit power generation cost, the power generation, the startup cost, the number of startups, the unit maintenance cost, the operating time, the unit carbon emissions, the carbon emission cost and preset constraints, solving the comprehensive cost minimization objective function to obtain the optimal solution of the function;

[0014] Based on the optimal solution of the function, determining an initial optimized energy scheduling scheme;

[0015] Acquire key parameters of power grid operation, perform sensitivity analysis on the key parameters of power grid operation, evaluate the impact of the key parameters of power grid operation on the initial optimized energy scheduling plan, and determine an adjusted energy scheduling plan;

[0016] In the case that the adjusted energy scheduling scheme does not satisfy the preset constraint conditions, the adjusted energy scheduling scheme is optimized until the adjusted energy scheduling scheme satisfies the preset constraint conditions, thereby obtaining a target energy scheduling scheme.

[0017] In one embodiment, the performing of sensitivity analysis on the key parameters of the power grid operation, evaluating the impact of the key parameters of the power grid operation on the initial optimized energy scheduling scheme, and determining the adjusted energy scheduling scheme includes:

[0018] Performing sensitivity analysis on the key parameters of the power grid operation to determine the sensitivity coefficients of the key parameters of the power grid operation;

[0019] Determining a key power grid operation parameter whose sensitivity coefficient is greater than or equal to a preset sensitivity threshold as an influencing parameter;

[0020] Based on the influencing parameters, the comprehensive cost minimization objective function is re-solved to obtain an adjusted energy scheduling plan.

[0021] In one embodiment, the performing sensitivity analysis on the key parameters of the power grid operation to determine the sensitivity coefficients of the key parameters of the power grid operation includes:

[0022] Substituting the key parameters of the power grid operation into the comprehensive cost minimization objective function to obtain the objective function value;

[0023] Obtaining a change parameter of the key operating parameter of the power grid within a preset time period, substituting the change parameter into the comprehensive cost minimization objective function, and obtaining a change amount of the objective function;

[0024] Obtaining a key parameter change amount according to the objective function value and the objective function change amount;

[0025] Determining the sensitivity coefficient of the key parameter of the power grid operation according to the change amount of the key parameter and the change amount of the objective function;

[0026] In one embodiment, the preset constraints include power generation constraints, dynamic transmission capacity constraints, load demand constraints, and safety margin constraints; and judging whether the adjusted energy scheduling scheme satisfies the preset constraints includes:

[0027] Determining whether the power generation of the power station in the power grid meets the power generation constraint condition after the adjusted energy scheduling plan is implemented;

[0028] Determining whether the transmission power of the transmission line in the power grid satisfies the dynamic transmission capacity constraint condition after the adjusted energy scheduling scheme is implemented;

[0029] Determining whether the load demand of the load point in the power grid meets the load demand constraint condition after the adjusted energy dispatching plan is implemented;

[0030] After the adjusted energy dispatching plan is implemented, it is determined whether the safety margin of the power station in the power grid satisfies the safety margin constraint condition.

[0031] In one embodiment, performing state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation state of the power grid includes:

[0032] extracting operation characteristic data from the operation data;

[0033] Taking the operation characteristic data as input, a graph neural network is called to perform state estimation on a pre-built power grid graph model to determine the operation state of the power grid.

[0034] In a second aspect, the present application also provides a power grid energy dispatching device, including:

[0035] A data acquisition module, used to acquire operation data;

[0036] An operation status determination module, configured to perform state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation status of the power grid, wherein the power grid diagram model is constructed based on the topological structure data and the power grid attribute data of the power grid;

[0037] A scheme generating module, used for generating an initial energy scheduling scheme according to the operating state of the power grid;

[0038] A scheme adjustment module is used to solve the comprehensive cost minimization objective function to obtain the optimal solution of the function, optimize and adjust the initial energy scheduling scheme based on the optimal solution of the function, and obtain an adjusted target energy scheduling scheme. The comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station;

[0039] An energy scheduling module is used to perform energy scheduling on the power grid based on the target energy scheduling scheme.

[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in any one of the above-mentioned power grid energy scheduling method embodiments when executing the computer program.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in any one of the above-mentioned embodiments of the power grid energy scheduling method are implemented.

[0042] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned power grid energy scheduling method embodiments.

[0043] The above-mentioned power grid energy scheduling method, device, computer equipment, computer-readable storage medium and computer program product are different from the traditional energy scheduling scheme that only considers minimizing the power generation cost to obtain the local optimal solution. This scheme, on the basis of constructing the objective function by minimizing the power generation cost, also considers the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station, and constructs an objective function that minimizes the comprehensive cost. It can obtain the global optimal solution and obtain a more accurate target energy scheduling scheme, and then perform energy scheduling according to the target energy scheduling scheme, which can effectively improve the energy scheduling efficiency and the operating efficiency of the power grid, and can also improve the overall stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 An application environment diagram of a power grid energy scheduling method in an embodiment;

[0046] Figure 2 A schematic diagram of a flow chart of a power grid energy dispatching method in one embodiment;

[0047] Figure 3 A schematic diagram of a flow chart of a power grid energy dispatching method in another embodiment;

[0048] Figure 4 A schematic diagram of a flow chart of steps for determining a target energy scheduling solution in one embodiment;

[0049] Figure 5 A schematic diagram of a flow chart of the steps of adjusting the energy scheduling scheme in one embodiment;

[0050] Figure 6 A schematic flow chart of a step of determining a sensitivity coefficient in another embodiment;

[0051] Figure 7 is a structural block diagram of a power grid energy dispatching device in one embodiment;

[0052] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] The grid energy scheduling method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the data acquisition terminal 100 and the terminal 102 communicate with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 is pre-built with a power grid diagram model, which is built based on the topological structure data and power grid attribute data of the power grid.

[0055] Specifically, the data acquisition terminal 100 may collect the operation data of the power grid in real time, and upload the collected operation data to the server 104. The power grid operator sends the power grid energy dispatch message to the server 104 through the terminal 102. The server 104 responds to the message, and estimates the state of the pre-built power grid diagram model according to the operation data to determine the operation state of the power grid. Then, according to the operation state of the power grid, an initial energy dispatch plan is generated, and then the comprehensive cost minimization objective function is solved to obtain the optimal solution of the function, and the initial energy dispatch plan is optimized and adjusted based on the optimal solution of the function to obtain the adjusted target energy dispatch plan. Finally, the power grid is dispatched based on the target energy dispatch plan. Among them, the comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station.

[0056] Among them, the data acquisition terminal 100 can be, but is not limited to, various sensors and data acquisition devices in the power grid. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0057] In an exemplary embodiment, Figure 2 As shown, a power grid energy scheduling method is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S100 to S900. Among them:

[0058] S100, obtaining operation data of the power grid.

[0059] The operation data of the power grid is the operation data of the power grid collected in real time by the data collection terminal. Specifically, the operation data includes the current power generation of each power station, the current load demand of each load point, the current transmission power of each transmission line and other data.

[0060] In actual applications, the data acquisition terminal in the power grid collects the operating data of power stations, load points and transmission lines in real time, and sends the collected operating data to the server in real time. The server receives and stores the above operating data in real time.

[0061] S300, performing state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation state of the power grid, wherein the power grid diagram model is constructed based on the topological structure data and the power grid attribute data of the power grid.

[0062] In this embodiment, the topological structure data of the power grid refers to data describing the connection relationship between various components (such as power stations, substations, load points, etc.) in the power system and the relative positions of these components in the power grid. In the power grid topology data, nodes represent the basic components of the power system, such as power stations, substations, load points, etc., and edges represent the electrical connections between nodes, usually transmission lines or transformers. The connection relationship describes which nodes are directly connected through edges, forming the basic network structure of the power grid.

[0063] The grid attribute data includes the physical attribute data, economic attribute data and operation attribute data of the grid. The physical attribute data includes the attribute data of power stations, substations, transmission lines and load points. For example, the power generation capacity, operating voltage and technical specification parameters of the power station, the transmission capacity, voltage level and equipment parameters of the substation, the load demand of the load point, etc. The economic attribute data includes the unit power generation cost, startup cost and maintenance cost, etc. The operation attribute data includes the operation status, historical operation data, etc.

[0064] In practical applications, the construction process of the power grid graph model is as follows: take each power station as a node, each load point as a node, and each substation as a node. Define the edges of the graph model: take each transmission line as an edge and connect the corresponding nodes. Add node attributes: add the power generation capacity, unit power generation cost, startup cost, maintenance cost and other attributes of the power station, add the load demand attribute of the load point, and add the transmission capacity, voltage level and other attributes of the substation. Add edge attributes: add the transmission capacity, resistance, reactance and other attributes of the transmission line. Finally, the power grid graph model is constructed based on nodes, edges, node attributes, and edge attributes.

[0065] In specific implementation, the server estimates the state of the power grid graph model to determine the current operating state of the power grid based on the operating data, including the current power generation of each power station, the current load demand of each load point, the current transmission power of each transmission line, etc. Specifically, the state of the power grid graph model can be estimated through a graph calculation algorithm to determine the state of each node and edge in the power grid. Specifically, the operating state includes data such as the power generation of the power station, the active and reactive power demand of the load point, and the active power and reactive power transmitted by the transmission line.

[0066] S500: Generate an initial energy scheduling plan according to the operating status of the power grid.

[0067] The initial energy dispatching scheme refers to a series of strategies and plans formulated to optimize the power generation, transmission and distribution process of the power grid. Following the above steps, after obtaining the operating status of the power grid, the initial energy dispatching scheme can be generated based on the operating status and comprehensively considering the operation of the power grid.

[0068] For example, if the load demand in a certain area suddenly increases, causing the voltage in that area to start to drop. Based on this information, the following measures can be taken to generate an initial energy scheduling plan:

[0069] 1. Increase the power generation of nearby power stations to meet the additional load demand;

[0070] 2. If the nearby power plants are already fully loaded, consider allocating power from other areas by changing the power flow direction of the transmission lines;

[0071] 3. Check whether there are backup power stations that can be started to supplement the power supply;

[0072] 4. In extreme cases, if the above measures are still not sufficient to solve the problem, we can consider implementing an orderly electricity consumption plan to temporarily reduce the power supply to some non-critical users.

[0073] S700, solve the comprehensive cost minimization objective function, obtain the optimal solution of the function, optimize and adjust the initial energy scheduling plan based on the optimal solution of the function, and obtain the adjusted target energy scheduling plan. The comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station.

[0074] The target energy scheduling scheme refers to an energy scheduling scheme obtained by optimizing and adjusting the initial energy scheduling scheme. The energy scheduling scheme enables the objective function to obtain the optimal solution while satisfying the constraints.

[0075] In this embodiment, the comprehensive cost minimization objective function (hereinafter referred to as the objective function) is an objective function constructed by comprehensively considering the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station. Specifically, the objective function is as follows:

[0076] ;

[0077] In the formula, min represents the minimization operation, represents the unit power generation cost of the ith power station, represents the power generation of the ith power station, represents the startup cost of the ith power station, represents the number of startups of the i-th power station, represents the unit maintenance cost of the ith power station, represents the operating time of the ith power station, represents the unit carbon emission cost of the i-th power station, represents the carbon emissions of the ith power station, and N represents the maximum amount of power generation. The objective function also includes multiple constraints, including power generation constraints, dynamic transmission capacity constraints, load demand constraints, and safety margin constraints.

[0078] In specific implementation, the server constructs a mathematical model based on the objective function and constraints, selects an optimization algorithm to solve the mathematical model, obtains the optimal solution of the function, and thus obtains the optimized and adjusted target energy scheduling plan. This step focuses on constructing a mathematical model through objective functions and constraints, and the solution of the mathematical model can refer to relevant existing technologies.

[0079] S900: Perform energy dispatch on the power grid based on the target energy dispatch scheme.

[0080] After the server obtains the target energy scheduling plan, it can generate scheduling instructions based on the target energy scheduling plan. Specifically, the target energy scheduling plan includes specifying the power generation and time schedule for each power station, adjusting the power flow distribution of the transmission line, optimizing network performance, deciding when to charge or discharge to smooth the load curve, and encouraging users to change their electricity consumption behavior to reduce pressure during peak hours. Based on the above target energy scheduling plan, the server sends the scheduling instructions to each execution unit through the automated control system, continuously tracks the actual operation of the power grid, and ensures execution as planned.

[0081] The above-mentioned power grid energy scheduling method is different from the traditional energy scheduling scheme that only considers minimizing the power generation cost and can only obtain a local optimal solution. This scheme, on the basis of constructing the objective function by minimizing the power generation cost, also considers the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station, and constructs an objective function that minimizes the comprehensive cost. It can obtain the global optimal solution and obtain a more accurate target energy scheduling scheme, and then perform energy scheduling according to the target energy scheduling scheme, which can effectively improve the energy scheduling efficiency, improve the operating efficiency of the power grid, and improve the overall stability of the power grid.

[0082] like Figure 3 As shown, in one of the embodiments, S300 includes: S320, extracting operating characteristic data from the operating data, taking the operating characteristic data as input, calling the graph neural network to perform state estimation on a pre-built power grid graph model, and determining the operating state of the power grid.

[0083] In this embodiment, a graph neural network architecture suitable for the task of power grid state estimation, such as Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), etc., can be pre-selected, the initial weights and other hyperparameters of the model can be set, and then the GNN model can be trained offline using historical data to optimize the model parameters so that it can accurately capture the dynamic characteristics of the power grid.

[0084] In specific implementation, after obtaining the operating data, the operating data is first preprocessed, including checking and cleaning up outliers and missing values ​​to ensure the integrity and accuracy of the data. Subsequently, useful operating features such as node voltage amplitude and phase angle, branch flow, etc. are extracted from the operating data, and the extracted operating features are standardized or normalized to obtain the input data of the graph neural network. The standardized or normalized operating features are then input into the trained graph neural network for rapid state estimation reasoning, determining the operating status of each node and edge in the power grid, and obtaining the operating status of the power grid. Furthermore, the graph neural network can be continuously fine-tuned according to the new operating data to maintain its good adaptability to the latest operating conditions.

[0085] In this embodiment, the graph neural network can effectively process complex power grid topology, capture the dependencies between nodes, and provide more accurate state estimation. In addition, the graph neural network has good generalization ability and can maintain a high estimation accuracy even in the face of incomplete or noisy data.

[0086] like Figure 4 As shown, in an exemplary embodiment, S700 includes:

[0087] S710, obtaining the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emission and carbon emission cost of the power station.

[0088] The server can obtain relevant attribute data of the power plant by connecting to the database or calling the interface, and extract information such as unit power generation cost, power generation, startup cost, number of starts, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost in advance.

[0089] S720, based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, carbon emission cost and preset constraints, solve the comprehensive cost minimization objective function to obtain the optimal solution of the function.

[0090] The server can substitute the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost into the objective function, select a suitable optimization algorithm (such as linear programming, mixed integer linear programming, genetic algorithm, etc.) to solve the objective function, use the selected algorithm to calculate the optimal solution for minimizing the comprehensive cost, and record the optimal solution of the function.

[0091] S730, determining an initial optimized energy scheduling scheme based on the optimal solution of the function.

[0092] After obtaining the optimal solution of the function, the optimal solution of the function is determined as the initial optimized energy scheduling solution.

[0093] S740, obtaining key parameters of power grid operation, performing sensitivity analysis on the key parameters of power grid operation, evaluating the impact of the key parameters of power grid operation on the initial optimized energy scheduling plan, and determining an adjusted energy scheduling plan.

[0094] The key parameters of power grid operation (hereinafter referred to as key detection parameters) refer to the key parameters screened from the operation data through operation data and historical operation data through correlation analysis, etc. For example, node voltage, line flow, load demand forecast, etc.

[0095] During the specific implementation, the sensitivity analysis method can be applied to evaluate the influence of these key parameters on the initial optimized energy scheduling plan. Specifically, the impact of different parameter changes on the cost, reliability, stability and other aspects of the scheduling plan can be analyzed. According to the results of the sensitivity analysis, the initial optimized energy scheduling plan can be adjusted.

[0096] S750, when the adjusted energy scheduling plan does not satisfy the preset constraint conditions, optimize the adjusted energy scheduling plan until the adjusted energy scheduling plan satisfies the preset constraint conditions, thereby obtaining a target energy scheduling plan.

[0097] After adjusting the initial optimized energy scheduling plan, it can be checked whether the adjusted energy scheduling plan meets all preset constraints. If the constraints are not met, the optimization problem is re-solved by adjusting variables (such as power generation allocation, startup plan, etc.) until a plan that meets all constraints is found. When the adjusted initial optimized energy scheduling plan meets all preset constraints, it is confirmed as the target energy scheduling plan. Furthermore, the finalized target energy scheduling plan can be sent to the power grid control system to guide the actual operation.

[0098] In this embodiment, a series of tasks from data acquisition, optimization solution, solution generation to final implementation ensure that the power grid energy dispatch plan not only meets economic and technical requirements, but also can cope with real-time changing operating conditions.

[0099] like Figure 5 As shown, in one embodiment, S740 includes:

[0100] S742, performing sensitivity analysis on key parameters of power grid operation to determine sensitivity coefficients of key parameters of power grid operation.

[0101] The sensitivity coefficient measures the degree of influence of a specific input parameter (such as node voltage, line flow, etc.) on the output (such as power generation cost, carbon emissions, etc.). It is usually expressed as the change in output when the parameter changes by a unit amount. Sensitivity analysis of key parameters of power grid operation is to study the change in output results when the input parameters change slightly, and is used to evaluate the impact of key parameters of power grid operation on energy scheduling schemes.

[0102] Specifically, each key parameter may be slightly disturbed to observe its effect on the output of the scheduling solution, and the sensitivity coefficient may be calculated by linear regression or other methods.

[0103] S744: Determine the key parameters of the power grid operation whose sensitivity coefficients are greater than or equal to a preset sensitivity threshold as influencing parameters.

[0104] Influencing parameters refer to key parameters whose sensitivity coefficients exceed the preset sensitivity thresholds. These parameters have a significant impact on the energy scheduling scheme and require special attention and adjustment. The sensitivity threshold is a threshold of the sensitivity coefficient set based on experience and expertise, which is used to distinguish which parameters have a significant impact. In this embodiment, a value that is higher than the middle value is selected as the threshold so that the influencing parameters that have an impact on the adjusted energy scheduling scheme can be accurately screened out.

[0105] Specifically, the sensitivity coefficient of each key parameter may be compared with a preset sensitivity threshold, and key parameters greater than or equal to the sensitivity threshold may be defined as influencing parameters, while key parameters with a sensitivity coefficient less than the preset sensitivity threshold may be defined as non-influencing parameters.

[0106] S746, based on the influencing parameters, re-solve the comprehensive cost minimization objective function to obtain an adjusted energy scheduling plan.

[0107] After screening out the influencing parameters, the influencing parameters can be incorporated into the comprehensive cost minimization objective function, and the comprehensive cost minimization problem can be re-solved using the optimization algorithm to find a new optimal solution. Based on the newly obtained optimal solution, an adjusted energy scheduling plan can be generated.

[0108] In this embodiment, through sensitivity analysis, the key parameters that have a significant impact on the energy scheduling plan can be more accurately identified, thereby improving the scientificity and accuracy of the scheduling decision, and the scheduling plan can be flexibly adjusted according to the real-time changing key parameters, so that the scheduling plan can better adapt to the actual operating conditions.

[0109] There are many ways to solve the sensitivity coefficient, such as Figure 6 As shown, in one embodiment, S742 includes:

[0110] S7422, substituting the key parameters of the power grid operation into the comprehensive cost minimization objective function to obtain the objective function value.

[0111] It can be understood that the objective function value is the calculation result of the objective function when a set of inputs (i.e., key parameters of grid operation) is given, which represents the comprehensive cost under the current dispatch scheme.

[0112] Specifically, after obtaining the key parameters of the power grid operation, the key parameters of the power grid operation are substituted into the comprehensive cost minimization objective function for calculation to obtain the objective function value.

[0113] S7424, obtaining the change parameters of the key parameters of the power grid operation within the preset time period, substituting the change parameters into the comprehensive cost minimization objective function, and obtaining the change amount of the objective function.

[0114] The change parameters reflect the actual changes in key parameters of power grid operation within a preset time period.

[0115] Specifically, the changes in the key parameters of the power grid operation after a period of time are obtained, and the changes in the key parameters of each power grid operation are extracted to obtain the change parameters. Then, the change parameters are gradually substituted into the comprehensive cost minimization objective function to simulate the impact of these changes on the power grid operation, and the changes in the objective function value after each substitution are compared with the initial objective function value to obtain the objective function change.

[0116] S7426, obtain the key parameter change according to the objective function value and the objective function change.

[0117] For each key parameter, by comparing the objective function value before and after the change, the corresponding key parameter change is calculated. That is, it is determined which key parameter changes directly lead to the change of the objective function value and the degree of such change is quantified.

[0118] S7428, determining the sensitivity coefficient of the key parameters of the power grid operation according to the changes of the key parameters and the changes of the objective function.

[0119] Specifically, for each key parameter of the power grid operation, linear regression or other statistical methods can be used to calculate its sensitivity coefficient based on the change amount of the key parameter and the corresponding change amount of the objective function. Subsequently, the sensitivity coefficient is compared with a preset sensitivity threshold, and the key parameter with a higher sensitivity coefficient is used as an influencing parameter.

[0120] In this embodiment, by performing a detailed analysis of the changes in key parameters and objective functions, the impact of each parameter on the comprehensive cost can be more accurately evaluated, and an accurate sensitivity coefficient can be obtained, thereby improving the scientificity and accuracy of scheduling decisions.

[0121] In one embodiment, determining whether the adjusted energy scheduling scheme satisfies a preset constraint condition includes:

[0122] Determine whether the power generation of the power station in the power grid meets the power generation constraint after the adjusted energy scheduling plan is implemented.

[0123] Determine whether the transmission power of the transmission lines in the power grid meets the dynamic transmission capacity constraint after the adjusted energy scheduling plan is implemented.

[0124] Determine whether the load demand of the load point in the power grid meets the load demand constraint conditions after the adjusted energy dispatch plan is implemented.

[0125] Determine whether the safety margin of the power station in the power grid meets the safety margin constraint after the adjusted energy dispatch plan is implemented.

[0126] As described in the above embodiment, the preset constraints include power generation constraints, dynamic transmission capacity constraints, load demand constraints and safety margin constraints. Specifically, they are as follows:

[0127] Power generation constraints:

[0128] ;

[0129] Dynamic transmission capacity constraints:

[0130] ;

[0131] Load demand constraints:

[0132] ;

[0133] Safety margin constraints:

[0134] ;

[0135] In the formula, represents the power generation of the ith power station at time t, represents the minimum power generation of the ith power station at time t, represents the maximum power generation of the ith power station at time t; represents the transmission power of the jth transmission line in the i-th power station at time t, represents the maximum transmission power of the jth transmission line in the i-th power station at time t, represents the load demand of the kth load point, M represents the maximum number of load points, T represents the time set, Represents the safety margin of the i-th power station.

[0136] In specific implementation, after obtaining the adjusted energy scheduling plan, the maximum / minimum power generation capacity, current power generation and other information of each power station are extracted from the database. According to the adjusted scheduling plan, the expected power generation of each node (power station) is calculated, and it is determined whether the expected power generation of each power station meets the above-mentioned power generation constraint conditions, that is, the power generation is between the maximum and minimum power generation capacities.

[0137] Collect the dynamic transmission capacity limit of each transmission line, use the power system simulation tool to simulate the power flow distribution after the implementation of the adjusted scheduling plan, calculate the actual transmission power of each transmission line, compare the actual transmission power with the dynamic transmission capacity limit, and confirm whether it exceeds the limit.

[0138] Obtain the demand forecast value of each load point, calculate the expected power supply of each load point according to the adjusted scheduling plan, and check whether the expected power supply of each load point can meet its demand and whether there is a power shortage.

[0139] After the adjusted scheduling scheme is implemented, the safety margin indicators of each node (such as voltage deviation, frequency stability, etc.) are calculated through simulation tools to check whether the safety margin of all nodes is within the allowable range.

[0140] Specifically, only when the adjusted energy scheduling scheme satisfies all the above constraints after implementation, the adjusted energy scheduling scheme is judged to satisfy the constraints and is determined as the target energy for output. If there is any unsatisfied constraint, the specific problem node or line is analyzed and determined, and the nodes, transmission lines, and load points that do not satisfy the constraints are readjusted to within the constraints, and the relevant data of the adjusted nodes, transmission lines, and load points are re-solved to obtain the optimized energy scheduling scheme. The optimized energy scheduling scheme is applied to the actual power grid, and it is judged again whether the adjusted energy scheduling scheme satisfies the above constraints after implementation, until the adjusted energy scheduling scheme satisfies all the above constraints after implementation. Any abnormality in the operation of the power grid can be adjusted in real time through the logic of this embodiment to improve the scheduling efficiency.

[0141] In this embodiment, by setting multiple key constraints and performing detailed simulation and calculation on the adjusted energy scheduling plan, the satisfaction of each constraint can be accurately evaluated, and adjustments can be made quickly when it is found that the constraints are not met, thereby enhancing the adaptability and response speed of the system and improving the comprehensiveness and completeness of the energy scheduling plan.

[0142] In order to make a clearer description of the power grid energy dispatching method provided by the present application, a specific embodiment is described below, and the specific embodiment includes the following steps:

[0143] S1, obtain the operation data of the power grid.

[0144] S2, extracts the operating characteristic data from the operating data, takes the operating characteristic data as input, calls the graph neural network to perform state estimation on the pre-built power grid graph model, and determines the operating state of the power grid. The power grid graph model is constructed based on the topological structure data and power grid attribute data of the power grid.

[0145] S3: Generate an initial energy scheduling plan based on the operating status of the power grid.

[0146] S4, obtains the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost of the power station.

[0147] S5, based on unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, carbon emission cost and preset constraints, solves the comprehensive cost minimization objective function and obtains the optimal solution of the function.

[0148] S6, based on the optimal solution of the function, determine the initial optimized energy scheduling plan.

[0149] S7, substituting the key parameters of power grid operation into the comprehensive cost minimization objective function to obtain the objective function value.

[0150] S8, obtaining the change parameters of the key parameters of the power grid operation within the preset time period, substituting the change parameters into the comprehensive cost minimization objective function, and obtaining the change amount of the objective function.

[0151] S9, obtaining the change of key parameters according to the objective function value and the change of the objective function.

[0152] S10, determining the sensitivity coefficient of the key parameters of the power grid operation according to the change amount of the key parameters and the change amount of the objective function.

[0153] S11, determining a key power grid operation parameter whose sensitivity coefficient is greater than or equal to a preset sensitivity threshold as an influencing parameter.

[0154] S12, based on the influencing parameters, re-solve the comprehensive cost minimization objective function to obtain the adjusted energy scheduling plan.

[0155] S13, determine whether the adjusted energy scheduling plan meets the preset constraints. If the adjusted energy scheduling plan does not meet the preset constraints, optimize the adjusted energy scheduling plan until the adjusted energy scheduling plan meets the preset constraints, thereby obtaining the target energy scheduling plan.

[0156] S14, performing energy scheduling on the power grid based on the target energy scheduling plan.

[0157] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0158] Based on the same inventive concept, the embodiment of the present application also provides a power grid energy dispatching device for implementing the power grid energy dispatching method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid energy dispatching device embodiments provided below can refer to the limitations of the power grid energy dispatching method above, and will not be repeated here.

[0159] In an exemplary embodiment, Figure 7 As shown, a power grid energy dispatching device 700 is provided, comprising: a data acquisition module 710, an operation status determination module 720, a scheme generation module 730, a scheme adjustment module 740 and an energy dispatching module 750, wherein:

[0160] The data acquisition module 710 is used to acquire operation data.

[0161] The operation status determination module 720 is used to perform state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation status of the power grid. The power grid diagram model is constructed based on the topological structure data and the power grid attribute data of the power grid.

[0162] The plan generation module 730 is used to generate an initial energy scheduling plan according to the operating status of the power grid.

[0163] The scheme adjustment module 740 is used to solve the comprehensive cost minimization objective function, obtain the optimal solution of the function, optimize and adjust the initial energy scheduling scheme based on the optimal solution of the function, and obtain the adjusted target energy scheduling scheme. The comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station.

[0164] The energy scheduling module 750 is used to perform energy scheduling on the power grid based on the target energy scheduling scheme.

[0165] In one embodiment, the scheme adjustment module 740 is also used to obtain the unit power generation cost, power generation, startup cost, number of starts, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost of the power station, and solve the comprehensive cost minimization objective function based on the unit power generation cost, power generation, startup cost, number of starts, unit maintenance cost, operating time, unit carbon emissions, carbon emission cost and preset constraints to obtain the optimal solution of the function, determine the initial optimized energy scheduling scheme based on the optimal solution of the function, obtain key parameters of power grid operation, perform sensitivity analysis on the key parameters of power grid operation, evaluate the impact of the key parameters of power grid operation on the initial optimized energy scheduling scheme, determine the adjusted energy scheduling scheme, and if the adjusted energy scheduling scheme does not meet the preset constraints, optimize the adjusted energy scheduling scheme until the adjusted energy scheduling scheme meets the preset constraints to obtain the target energy scheduling scheme.

[0166] In one of the embodiments, the scheme adjustment module 740 is also used to perform sensitivity analysis on key parameters of power grid operation to determine the sensitivity coefficients of the key parameters of power grid operation; determine the key parameters of power grid operation whose sensitivity coefficients are greater than or equal to a preset sensitivity threshold as influencing parameters; based on the influencing parameters, re-solve the comprehensive cost minimization objective function to obtain an adjusted energy scheduling scheme.

[0167] In one embodiment, the scheme adjustment module 740 is further used to substitute the key parameters of the power grid operation into the comprehensive cost minimization objective function to obtain the objective function value; obtain the change parameters of the key parameters of the power grid operation within a preset time period, substitute the change parameters into the comprehensive cost minimization objective function to obtain the objective function change; obtain the key parameter change according to the objective function value and the objective function change; determine the sensitivity coefficient of the key parameters of the power grid operation according to the key parameter change and the objective function change;

[0168] In one embodiment, the preset constraints include power generation constraints, dynamic transmission capacity constraints, load demand constraints and safety margin constraints; the scheme adjustment module 740 is also used to determine whether the power generation of the power station in the power grid meets the power generation constraints after the adjusted energy scheduling scheme is implemented; determine whether the transmission power of the transmission line in the power grid meets the dynamic transmission capacity constraints after the adjusted energy scheduling scheme is implemented; determine whether the load demand of the load point in the power grid meets the load demand constraints after the adjusted energy scheduling scheme is implemented; determine whether the safety margin of the power station in the power grid meets the safety margin constraints after the adjusted energy scheduling scheme is implemented.

[0169] In one embodiment, the operating status determination module 720 is used to extract operating characteristic data from the operating data, take the operating characteristic data as input, call the graph neural network to perform state estimation on the pre-built power grid graph model, and determine the operating status of the power grid.

[0170] Each module in the above-mentioned power grid energy dispatching device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0171] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the operation data of the power grid, the energy scheduling scheme, etc. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power grid energy scheduling method is implemented.

[0172] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned embodiments of the power grid energy scheduling method are implemented.

[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above-mentioned power grid energy scheduling method embodiments are implemented.

[0175] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned power grid energy scheduling method embodiments.

[0176] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0177] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0178] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0179] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A power grid energy dispatching method, characterized in that: The method comprises: Obtaining the operation data of the power grid; Performing state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation state of the power grid, wherein the power grid diagram model is constructed based on the topological structure data and the power grid attribute data of the power grid; generating an initial energy scheduling plan according to the operating status of the power grid; Solving the comprehensive cost minimization objective function to obtain the optimal solution of the function, optimizing and adjusting the initial energy scheduling plan based on the optimal solution of the function to obtain an adjusted target energy scheduling plan, wherein the comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station; Energy scheduling is performed on the power grid based on the target energy scheduling scheme.

2. The method according to claim 1, characterized in that The method of solving the comprehensive cost minimization objective function to obtain the optimal solution of the function, and optimizing and adjusting the initial energy scheduling scheme based on the optimal solution of the function to obtain the adjusted target energy scheduling scheme includes: Obtain the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions and carbon emission cost of the power station; Based on the unit power generation cost, the power generation, the startup cost, the number of startups, the unit maintenance cost, the operating time, the unit carbon emissions, the carbon emission cost and preset constraints, solving the comprehensive cost minimization objective function to obtain the optimal solution of the function; Based on the optimal solution of the function, determining an initial optimized energy scheduling scheme; Acquire key parameters of power grid operation, perform sensitivity analysis on the key parameters of power grid operation, evaluate the impact of the key parameters of power grid operation on the initial optimized energy scheduling plan, and determine an adjusted energy scheduling plan; In the case that the adjusted energy scheduling scheme does not satisfy the preset constraint conditions, the adjusted energy scheduling scheme is optimized until the adjusted energy scheduling scheme satisfies the preset constraint conditions, thereby obtaining a target energy scheduling scheme.

3. The method according to claim 2, characterized in that The performing of sensitivity analysis on the key parameters of the power grid operation, evaluating the influence of the key parameters of the power grid operation on the initial optimized energy scheduling scheme, and determining the adjusted energy scheduling scheme includes: Performing sensitivity analysis on the key parameters of the power grid operation to determine the sensitivity coefficients of the key parameters of the power grid operation; Determining a key power grid operation parameter whose sensitivity coefficient is greater than or equal to a preset sensitivity threshold as an influencing parameter; Based on the influencing parameters, the comprehensive cost minimization objective function is re-solved to obtain an adjusted energy scheduling plan.

4. The method according to claim 3, characterized in that The performing sensitivity analysis on the key parameters of the power grid operation to determine the sensitivity coefficients of the key parameters of the power grid operation includes: Substituting the key parameters of the power grid operation into the comprehensive cost minimization objective function to obtain the objective function value; Obtaining a change parameter of the key operating parameter of the power grid within a preset time period, substituting the change parameter into the comprehensive cost minimization objective function, and obtaining a change amount of the objective function; Obtaining a key parameter change amount according to the objective function value and the objective function change amount; The sensitivity coefficient of the key parameter of the power grid operation is determined according to the change amount of the key parameter and the change amount of the objective function.

5. The method according to claim 2, characterized in that: The preset constraints include power generation constraints, dynamic transmission capacity constraints, load demand constraints and safety margin constraints; Determining whether the adjusted energy scheduling scheme satisfies the preset constraint condition includes: Determining whether the power generation of the power station in the power grid meets the power generation constraint condition after the adjusted energy scheduling plan is implemented; Determining whether the transmission power of the transmission line in the power grid satisfies the dynamic transmission capacity constraint condition after the adjusted energy scheduling scheme is implemented; Determining whether the load demand of the load point in the power grid meets the load demand constraint condition after the adjusted energy dispatching plan is implemented; After the adjusted energy dispatching plan is implemented, it is determined whether the safety margin of the power station in the power grid satisfies the safety margin constraint condition.

6. The method according to any one of claims 1 to 5, characterized in that: The performing state estimation on the pre-constructed power grid diagram model according to the operation data to determine the operation state of the power grid includes: extracting operation characteristic data from the operation data; Taking the operation characteristic data as input, a graph neural network is called to perform state estimation on a pre-built power grid graph model to determine the operation state of the power grid.

7. A power grid energy dispatching device, characterized in that: The device comprises: A data acquisition module, used to acquire operation data; An operation status determination module, configured to perform state estimation on a pre-constructed power grid diagram model according to the operation data to determine the operation status of the power grid, wherein the power grid diagram model is constructed based on the topological structure data and the power grid attribute data of the power grid; A scheme generating module, used for generating an initial energy scheduling scheme according to the operating state of the power grid; A scheme adjustment module is used to solve the comprehensive cost minimization objective function to obtain the optimal solution of the function, optimize and adjust the initial energy scheduling scheme based on the optimal solution of the function, and obtain an adjusted target energy scheduling scheme. The comprehensive cost minimization objective function is constructed based on the unit power generation cost, power generation, startup cost, number of startups, unit maintenance cost, operating time, unit carbon emissions, and carbon emission cost of the power station; An energy scheduling module is used to perform energy scheduling on the power grid based on the target energy scheduling scheme.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images