Day-ahead, intra-day and real-time multi-level power generation plan generation method and system

Abstract

The invention relates to the technical field of power generation plan generation, in particular to a day-ahead, intra-day and real-time multi-level power generation plan generation method and system. The scheme comprises the following steps: acquiring historical load data, and acquiring a current power generation plan in real time; establishing an analysis mathematical model including generator set characteristics, a power grid structure and market demands; establishing a mapping model of power emission and loss in the whole system; the method comprises the following steps: decomposing an original power generation plan into a day-ahead sub-plan, an intra-day sub-plan and a real-time sub-plan in a layered disassembly mode; setting a preset optimization algorithm, and performing layer-by-layer optimization on the day-ahead sub-plan, the day-in sub-plan and the real-time sub-plan; and updating a power generation plan according to a layer-by-layer optimization result and real-time data The scheme is used for accurately predicting power load and renewable energy output. According to the method, modes and trends in the data can be captured, and the prediction accuracy is improved, so that a reliable basis is provided for making a reasonable power generation plan.

Description

Technical Field

[0001] The present invention relates to the technical field of power generation plan generation, and more specifically, to a method and system for generating a multi-level power generation plan on a day-ahead, intra-day and real-time basis. Background Art

[0002] In the field of power generation plan generation, the generation method of multi-level power generation plans at the day-ahead, intraday and real-time levels is to use advanced forecasting technology and optimization algorithms, combined with the actual operation of the power system and market demand, to formulate power generation scheduling plans at different time scales. The significance of this method is that it can improve the operating efficiency and stability of the power system, reduce operating costs, and ensure the reliability and security of power supply. Its importance is reflected in the fact that it plays an indispensable role in promoting the rational use of energy, supporting large-scale access to renewable energy, and responding to rapid changes in the power market. It is a key component of the construction and development of modern smart grids.

[0003] Prior to the technology of the present invention, existing methods for generating multi-level power generation plans on the day before, within the day, and in real time mainly relied on deterministic forecasting models and optimization algorithms. These methods usually use traditional mathematical optimization tools such as linear programming and mixed integer linear programming to formulate power generation plans. However, the complexity and uncertainty of the power system pose many challenges to these methods. The technical difficulty lies in how to accurately predict changes in power load, renewable energy output, and market prices, while also taking into account the safety constraints and operating costs of the system. In addition, plans at different time scales need to be effectively coordinated to ensure overall optimality and feasibility. The key points include developing more accurate forecasting models to cope with uncertainty, designing efficient optimization algorithms that can handle large-scale problems, and achieving dynamic coordination and balance between multiple time scales. Summary of the invention

[0004] In view of the above problems, the present invention proposes a method and system for generating multi-level power generation plans for the day-ahead, intra-day and real-time, which is used to accurately predict power load and renewable energy output. This method can capture patterns and trends in data, improve the accuracy of prediction, and thus provide a reliable basis for formulating reasonable power generation plans.

[0005] According to a first aspect of an embodiment of the present invention, a method for generating a day-ahead, intra-day and real-time multi-level power generation plan is provided.

[0006] In one or more embodiments, preferably, the method for generating a day-ahead, intra-day and real-time multi-level power generation plan includes:

[0007] Obtain historical load data and collect current power generation plans in real time;

[0008] Establish analytical mathematical models that include generator characteristics, grid structure, and market demand;

[0009] Establish a mapping model of power generation and loss in the entire system;

[0010] The original power generation plan is decomposed into three sub-plans: day-ahead, intra-day and real-time.

[0011] Set the preset optimization algorithm to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer;

[0012] Based on the optimization results layer by layer, the power generation plan is updated with real-time data.

[0013] In one or more embodiments, preferably, the acquiring of historical load data and real-time acquisition of the current power generation plan specifically includes:

[0014] Extract historical load data from energy management systems or distribution automation systems;

[0015] Clean and preprocess the collected historical data to remove outliers or incomplete records to ensure data quality and consistency;

[0016] Configure a real-time data acquisition system to obtain current generation plans and real-time load data from the power plant's control system or market operation center.

[0017] In one or more embodiments, preferably, the establishing of an analytical mathematical model including generator set characteristics, grid structure and market demand specifically includes:

[0018] According to the type of generator set, a corresponding analytical mathematical model is established to describe its operating characteristics;

[0019] Build analytical mathematical models of the power grid and determine market demand.

[0020] In one or more embodiments, preferably, establishing a mapping model of power emission and loss in the entire system specifically includes:

[0021] Analyze each core device according to the analytical mathematical model to determine the relationship between its loss and output power;

[0022] The mapping relationship between the loss and the emitted power is set as a mapping model.

[0023] In one or more embodiments, preferably, the original power generation plan is decomposed into three sub-plans, namely, day-ahead, intra-day and real-time, in a hierarchical manner, specifically including:

[0024] Get the original power generation plan, first split the day-ahead plan, and obtain the part of the current power generation plan that has been determined the day before as the day-ahead power generation plan component;

[0025] Get the original power generation plan and determine the new adjustments generated within the current day as the incoming plan component;

[0026] Based on the real-time voltage trading volume of 5-15 minutes, the latest power generation plan changes formed in real time are set as real-time plans.

[0027] In one or more embodiments, preferably, the preset optimization algorithm is set to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer, specifically including:

[0028] After obtaining the day-ahead sub-plan, the first calculation formula is used to calculate the imbalance between the day-ahead plan and the model;

[0029] Determine whether the second calculation formula is satisfied, and then use the third calculation formula to generate the intraday adjustment basis;

[0030] After obtaining the intra-day sub-plan, the power output of the adjusted intra-day plan is generated using the fourth calculation formula;

[0031] According to the power output of the adjusted intraday plan, using the mathematical model of power generation and loss, it is determined whether the fifth calculation formula is satisfied. If not, the preset demand is satisfied by adjusting the intraday plan;

[0032] The carbon saving capacity is calculated using the sixth calculation formula, and the output of the equipment is adjusted in real time according to the maximum carbon saving capacity;

[0033] The first calculation formula is:

[0034]

[0035] Among them, BJ is the imbalance between the day-ahead plan and the model, Pi is the loss estimation deviation of the i-th node under the day-ahead plan, and n is the total number of nodes;

[0036] The second calculation formula is:

[0037] BJ>Y

[0038] Where, Y is the mismatch contrast margin;

[0039] The third calculation formula is:

[0040] J=KT-PC

[0041] Among them, J is the intraday adjustment benchmark, KT is the adjustable power demand, PC is the loss deviation and;

[0042] The fourth calculation formula is:

[0043] Th=tq+J

[0044] Among them, th is the power output of the adjusted intraday plan, and tq is the power output of the intraday sub-plan;

[0045] The fifth calculation formula is:

[0046] SZ <Y4

[0047] GXD>Y5

[0048] Among them, SZ is the total loss, GXD is the power demand responsiveness, Y4 is the loss limit margin, and Y5 is the response speed margin;

[0049] The sixth calculation formula is:

[0050] TJ=S15÷XQ15

[0051] Among them, TJ is the carbon saving capacity, S15 is the total power generation of new energy within 15 minutes, and XQ15 is the power supply demand circuit within 15 minutes.

[0052] In one or more embodiments, preferably, updating the power generation plan with real-time data based on the layer-by-layer optimization results specifically includes:

[0053] Get the optimized day-ahead, intraday, and real-time sub-plans;

[0054] Update the intraday sub-plan and the day-ahead sub-plan separately;

[0055] Dynamic execution of real-time sub-plans.

[0056] According to a second aspect of an embodiment of the present invention, a day-ahead, intra-day and real-time multi-level power generation plan generation system is provided.

[0057] In one or more embodiments, preferably, the day-ahead, intra-day and real-time multi-level power generation plan generation system includes:

[0058] Data collection module, used to obtain historical load data and collect current power generation plans in real time;

[0059] Load forecasting module, used to establish analytical mathematical models that include generator characteristics, grid structure and market demand;

[0060] Mathematical modeling module, used to establish a mapping model of power generation and loss in the entire system;

[0061] The hierarchical optimization module is used to decompose the original power generation plan into three sub-plans: day-ahead, intraday and real-time.

[0062] The genetic algorithm module is used to set the preset optimization algorithm and optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer;

[0063] The dynamic adjustment module is used to update the power generation plan based on the layer-by-layer optimization results and real-time data.

[0064] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0065] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement any one of the methods described in the first aspect of the embodiment of the present invention.

[0066] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0067] In the solution of the present invention, the problem is decomposed into three sub-problems: day-ahead, intra-day and real-time, and solved separately. This strategy can reduce the complexity of the problem, making each sub-problem easier to handle, while ensuring the optimality and feasibility of the overall solution.

[0068] In the solution of the present invention, the optimal solution is automatically found for each sub-problem, which is suitable for solving multi-objective and multi-constraint optimization problems.

[0069] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0070] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0072] Figure 1 The present invention is a flowchart of a method for generating a multi-level power generation plan on a day-ahead, intra-day and real-time basis according to an embodiment of the present invention.

[0073] Figure 2 It is a flowchart of acquiring historical load data and collecting the current power generation plan in real time in a method for generating a multi-level power generation plan on the day before, within the day and in real time in one embodiment of the present invention.

[0074] Figure 3 It is a flow chart of establishing an analytical mathematical model including generator set characteristics, grid structure and market demand in a method for generating a multi-level power generation plan on the day-ahead, intra-day and real-time basis in one embodiment of the present invention.

[0075] Figure 4 It is a flowchart of establishing a mapping model of power generation and loss in the entire system in a method for generating a multi-level power generation plan on the day-ahead, intra-day and real-time basis in one embodiment of the present invention.

[0076] Figure 5 It is a flowchart of a method for generating a multi-level power generation plan of day-ahead, intra-day and real-time in an embodiment of the present invention, which decomposes an original power generation plan into three sub-plans of day-ahead, intra-day and real-time by means of layered decomposition.

[0077] Figure 6 It is a flowchart of setting a preset optimization algorithm in a method for generating a multi-level power generation plan of the day-ahead, intra-day and real-time in one embodiment of the present invention, and optimizing the three sub-plans of the day-ahead, intra-day and real-time layer by layer.

[0078] Figure 7 It is a flowchart of updating the power generation plan with real-time data according to the layer-by-layer optimization results in a method for generating a multi-level power generation plan for the day-ahead, intra-day and real-time according to an embodiment of the present invention.

[0079] Figure 8 It is a structural diagram of a system for generating a multi-level power generation plan for the day-ahead, intra-day and real-time according to an embodiment of the present invention.

[0080] Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0081] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0083] In the field of power generation plan generation, the generation method of multi-level power generation plans at the day-ahead, intraday and real-time levels is to use advanced forecasting technology and optimization algorithms, combined with the actual operation of the power system and market demand, to formulate power generation scheduling plans at different time scales. The significance of this method is that it can improve the operating efficiency and stability of the power system, reduce operating costs, and ensure the reliability and security of power supply. Its importance is reflected in the fact that it plays an indispensable role in promoting the rational use of energy, supporting large-scale access to renewable energy, and responding to rapid changes in the power market. It is a key component of the construction and development of modern smart grids.

[0084] Prior to the technology of the present invention, existing methods for generating multi-level power generation plans on the day before, within the day, and in real time mainly relied on deterministic forecasting models and optimization algorithms. These methods usually use traditional mathematical optimization tools such as linear programming and mixed integer linear programming to formulate power generation plans. However, the complexity and uncertainty of the power system pose many challenges to these methods. The technical difficulty lies in how to accurately predict changes in power load, renewable energy output, and market prices, while also taking into account the safety constraints and operating costs of the system. In addition, plans at different time scales need to be effectively coordinated to ensure overall optimality and feasibility. The key points include developing more accurate forecasting models to cope with uncertainty, designing efficient optimization algorithms that can handle large-scale problems, and achieving dynamic coordination and balance between multiple time scales.

[0085] In the embodiment of the present invention, a method and system for generating a multi-level power generation plan for the day-ahead, intra-day and real-time are provided. The scheme is used to accurately predict power load and renewable energy output. This method can capture patterns and trends in data, improve the accuracy of prediction, and thus provide a reliable basis for formulating a reasonable power generation plan.

[0086] According to a first aspect of an embodiment of the present invention, a method for generating a day-ahead, intra-day and real-time multi-level power generation plan is provided.

[0087] Figure 1 The present invention is a flowchart of a method for generating a multi-level power generation plan on a day-ahead, intra-day and real-time basis according to an embodiment of the present invention.

[0088] In one or more embodiments, preferably, the method for generating a day-ahead, intra-day and real-time multi-level power generation plan includes:

[0089] S101, obtaining historical load data and collecting current power generation plans in real time;

[0090] S102, establishing an analytical mathematical model including characteristics of generator sets, grid structure and market demand;

[0091] S103, establishing a mapping model of power generation and loss in the entire system;

[0092] S104, decomposing the original power generation plan into three sub-plans: day-ahead, intra-day and real-time by using a layered decomposition method;

[0093] S105, setting a preset optimization algorithm, and optimizing the three sub-plans of day-ahead, intra-day and real-time layer by layer;

[0094] S106. Update the power generation plan based on the optimization results layer by layer and real-time data.

[0095] In an embodiment of the present invention, a comprehensive day-ahead, intraday and real-time multi-level power generation plan generation method and system are proposed. First, by collecting historical data and real-time information, advanced data analysis technology is used to perform load forecasting and renewable energy output forecasting to improve the accuracy of the forecast. Secondly, a detailed mathematical model including the characteristics of the generator set, the grid structure and the market demand is established as the basis of the optimization algorithm. Then, a hierarchical optimization strategy is adopted to decompose the problem into multiple sub-problems corresponding to different time scales to reduce the complexity of the problem and improve the solution efficiency. Then, a customized optimization algorithm is applied at each time scale to find the optimal power generation plan. In addition, a dynamic adjustment mechanism is introduced to update the prediction results and optimization model according to real-time data to ensure the real-time and adaptability of the plan. Finally, the effectiveness of the proposed method is verified through simulation tests and actual operation, and adjustments and optimizations are made according to feedback to achieve efficient and stable operation of the power system.

[0096] Figure 2 It is a flowchart of acquiring historical load data and collecting the current power generation plan in real time in a method for generating a multi-level power generation plan on the day before, within the day and in real time in one embodiment of the present invention.

[0097] like Figure 2 As shown, in one or more embodiments, preferably, the acquisition of historical load data and real-time collection of the current power generation plan specifically includes:

[0098] S201. Extracting historical load data from an energy management system or a distribution automation system;

[0099] S202, cleaning and preprocessing the collected historical data to remove outliers or incomplete records to ensure data quality and consistency;

[0100] S203. Configure a real-time data acquisition system to obtain current power generation plans and real-time load data from the control system of the power plant or the market operation center.

[0101] In an embodiment of the present invention, historical load data is first obtained through an energy management system (EMS) or a distribution automation system (DAS). These systems usually have the function of storing and recording the operating status of the power grid and can provide detailed load data. Next, the collected historical data is cleaned and preprocessed. This step includes operations such as removing outliers, filling missing data, and standardizing data formats to ensure the quality and consistency of the data. For example, if the load value of a record deviates significantly from other records, it can be regarded as an outlier and corrected or deleted. After completing data cleaning, a real-time data acquisition system is configured to obtain the current power generation plan and real-time load data from the control system of the power plant or the market operation center. This system needs to be connected to relevant equipment and set a suitable acquisition frequency to ensure that the latest data can be obtained in a timely manner. Through the above steps, accurate historical load data and real-time load data can be obtained to provide support for subsequent analysis and decision-making.

[0102] Figure 3 It is a flow chart of establishing an analytical mathematical model including generator set characteristics, grid structure and market demand in a method for generating a multi-level power generation plan on the day-ahead, intra-day and real-time basis in one embodiment of the present invention.

[0103] like Figure 3 As shown, in one or more embodiments, preferably, the establishment of an analytical mathematical model including the characteristics of the generator set, the grid structure and the market demand specifically includes:

[0104] S301, establishing a corresponding analytical mathematical model according to the type of the generator set to describe its operating characteristics;

[0105] S302. Establish an analytical mathematical model for the power grid and determine market demand.

[0106] In an embodiment of the present invention, a mathematical model including the characteristics of the generator set, the grid structure and the market demand is first established. For the characteristics of the generator set, corresponding mathematical models are established according to different types of generator sets (such as coal-fired units, gas turbines, hydropower generation, etc.) to describe their operating characteristics. These models can be constructed based on physical principles and empirical data to reflect the relationship between the output power of different types of units and the input fuel consumption. Next, a mathematical model of the power grid is established. This model needs to consider factors such as the structure of the power grid, the characteristics of the transmission line, and the loss during the power transmission process. By analyzing the topological structure and parameters of the power grid, the flow of electricity in the power grid can be determined, and the voltage and current of each node can be calculated. Finally, the market demand needs to be determined. Market demand generally refers to the user's demand for electricity, which can be analyzed and predicted through historical load data and real-time monitoring data. Time series analysis methods or other statistical methods can be used to estimate future market demand and incorporate it into the mathematical model. Through the above steps, a mathematical model that comprehensively considers the characteristics of the generator set, the grid structure and the market demand can be established to provide a basis for subsequent optimization and decision-making.

[0107] Figure 4 It is a flowchart of establishing a mapping model of power generation and loss in the entire system in a method for generating a multi-level power generation plan on the day-ahead, intra-day and real-time basis in one embodiment of the present invention.

[0108] like Figure 4 As shown, in one or more embodiments, preferably, the establishing of a mapping model of power emission and loss in the entire system specifically includes:

[0109] S401, analyzing each core equipment according to the analytical mathematical model to determine the relationship between its loss and output power;

[0110] S402: Set the mapping relationship between the loss and the output power as a mapping model.

[0111] In an embodiment of the present invention, a mapping model of power emission and loss in the entire system is first established. This model needs to take into account the characteristics and mutual relationships of each core equipment to determine the mapping relationship between its loss and emitted power. The specific steps are as follows: Analyze the characteristics of each core equipment: According to the mathematical model, each core equipment in the system is analyzed in detail. This includes understanding the technical parameters, operating status and correlation of the equipment with other equipment. Through this information, the loss characteristics of each equipment can be preliminarily determined. Determine the relationship between loss and emitted power: After analyzing each core equipment, it is necessary to further study the relationship between its loss and emitted power. This can be done through experimental data, theoretical calculations or empirical formulas. For example, for a generator, a regression model can be established by measuring its output power and corresponding losses under different loads to describe the mapping relationship between loss and emitted power. Set up a mapping model: Once the relationship between the loss and emitted power of each core equipment is determined, these relationships can be integrated into a unified mapping model. This model can be in the form of a mathematical equation, a table or a graph, etc., which is used to describe the corresponding relationship between power emission and loss in the entire system. Verify and optimize the model: Finally, the established mapping model needs to be verified and optimized. This can be achieved by comparing with actual operating data. If it is found that the results predicted by the model deviate greatly from the actual situation, it is necessary to adjust the model parameters or reconsider factors such as the characteristics of the equipment to improve the accuracy and reliability of the model. Through the above steps, a mapping model that accurately describes the relationship between power generation and loss in the entire system can be established, providing a basis for subsequent optimization and decision-making.

[0112] Figure 5 It is a flowchart of a method for generating a multi-level power generation plan of day-ahead, intra-day and real-time in an embodiment of the present invention, which decomposes an original power generation plan into three sub-plans of day-ahead, intra-day and real-time by means of layered decomposition.

[0113] like Figure 5 As shown, in one or more embodiments, preferably, the original power generation plan is decomposed into three sub-plans, namely, day-ahead, intra-day and real-time, in a hierarchical manner, specifically including:

[0114] S501, obtaining the original power generation plan, first splitting the day-ahead plan, and obtaining the part of the current power generation plan that has been determined the day-ahead as the day-ahead power generation plan component;

[0115] S502, obtaining the original power generation plan, and determining the new adjustment generated within the current day as the incoming plan component;

[0116] S503. Based on the real-time voltage transaction volume of 5-15 minutes, the latest power generation plan change formed in real time is set as the real-time plan.

[0117] In an embodiment of the present invention, the original power generation plan is decomposed into three sub-plans, namely, day-ahead, intraday and real-time, by means of hierarchical decomposition. The specific steps are as follows: Obtain the original power generation plan: First, obtain the current original power generation plan from the energy management system (EMS) or the distribution automation system (DAS). This plan contains the power generation arrangement and expected load conditions in the future. Perform day-ahead plan splitting: Next, the original power generation plan is split into day-ahead plan splitting. This means that it is necessary to identify the already determined parts of the current power generation plan and use them as the day-ahead power generation plan components. These already determined parts may include some stable factors such as long-term contracts and base load power generation. In this way, the stability and predictability of the day-ahead plan can be ensured. Determine intraday adjustments: Then, obtain the new adjustments generated within the day and use them as the day-ahead plan components. Intraday adjustments are usually made based on factors such as short-term market demand changes, weather conditions or other emergencies. These adjustments may include increasing or decreasing the output of certain generators to meet changes in real-time load demand. Real-time plan changes: Finally, based on the real-time voltage trading volume of 5-15 minutes, the latest power generation plan changes formed in real time are set as real-time plans. The real-time plan is the result of dynamic adjustment based on the grid operation status and real-time load conditions. It can be automatically generated by monitoring grid frequency, voltage and other parameters according to preset rules and algorithms. The goal of the real-time plan is to maintain the balance and stable operation of the power system. Through the above steps, the original power generation plan is decomposed into three sub-plans: day-ahead, intraday and real-time.

[0118] Figure 6 It is a flowchart of setting a preset optimization algorithm in a method for generating a multi-level power generation plan of the day-ahead, intra-day and real-time in one embodiment of the present invention, and optimizing the three sub-plans of the day-ahead, intra-day and real-time layer by layer.

[0119] like Figure 6 As shown, in one or more embodiments, preferably, the preset optimization algorithm is set to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer, specifically including:

[0120] S601, after obtaining the day-ahead sub-plan, using the first calculation formula to calculate the imbalance between the day-ahead plan and the model;

[0121] S602: Determine whether the second calculation formula is satisfied, and then generate an intraday adjustment benchmark using a third calculation formula;

[0122] S603, after obtaining the intra-day sub-plan, using the fourth calculation formula to generate the power output of the adjusted intra-day plan;

[0123] S604, judging whether the fifth calculation formula is satisfied by using the mathematical model of power generation and loss according to the adjusted power output of the intraday plan, and if not, satisfying the preset demand by adjusting the intraday plan;

[0124] S605, calculating the carbon saving capacity using the sixth calculation formula, and adjusting the equipment output in real time according to the maximum carbon saving capacity;

[0125] The first calculation formula is:

[0126]

[0127] Among them, BJ is the imbalance between the day-ahead plan and the model, Pi is the loss estimation deviation of the i-th node under the day-ahead plan, and n is the total number of nodes;

[0128] The second calculation formula is:

[0129] BJ>Y

[0130] Where, Y is the mismatch contrast margin;

[0131] The third calculation formula is:

[0132] J=KT-PC

[0133] Among them, J is the intraday adjustment benchmark, KT is the adjustable power demand, PC is the loss deviation and;

[0134] The fourth calculation formula is:

[0135] Th=tq+J

[0136] Among them, th is the power output of the adjusted intraday plan, and tq is the power output of the intraday sub-plan;

[0137] The fifth calculation formula is:

[0138] SZ <Y4

[0139] GXD>Y5

[0140] Among them, SZ is the total loss, GXD is the power demand responsiveness, Y4 is the loss limit margin, and Y5 is the response speed margin;

[0141] The sixth calculation formula is:

[0142] TJ=S15÷XQ15

[0143] Among them, TJ is the carbon saving capacity, S15 is the total power generation of new energy within 15 minutes, and XQ15 is the power supply demand circuit within 15 minutes.

[0144] In an embodiment of the present invention, after obtaining the day-ahead sub-plan, the first calculation formula is used to calculate the imbalance between the day-ahead plan and the model match: First, the first calculation formula BJ=Σi=ni=1|Pi| is used to calculate the imbalance between the day-ahead plan and the model match. Among them, BJ represents the imbalance between the day-ahead plan and the model match, Pi represents the loss estimation deviation of the i-th node under the day-ahead plan, and n represents the total number of nodes. This formula obtains the imbalance of the entire system by summing the loss estimation deviations of each node. Determine whether the second calculation formula is satisfied, and then use the third calculation formula to generate the intraday adjustment benchmark: Next, determine whether the imbalance of the day-ahead plan satisfies the second calculation formula BJ>Y. If the condition is met, no further adjustment is required; if the condition is not met, the third calculation formula J=KT-PC is required to generate the intraday adjustment benchmark. Among them, J represents the intraday adjustment benchmark, KT represents the adjustable power demand, and PC represents the loss deviation sum. After obtaining the intraday sub-plan, the power output of the adjusted intraday plan is generated using the fourth calculation formula: Then, the intraday sub-plan is obtained, and the fourth calculation formula th=tq+J is used to generate the power output of the adjusted intraday plan. Among them, th represents the power output of the adjusted intraday plan, and tq represents the power output of the intraday sub-plan. According to the power output of the adjusted intraday plan, the mathematical model of power emission and loss is used to determine whether the fifth calculation formula is met. If not, the preset demand is met by adjusting the intraday plan: Next, according to the power output of the adjusted intraday plan, the mathematical model of power emission and loss is used to determine whether the fifth calculation formula SZY5 is met. If the condition is not met, it is necessary to meet the preset demand through the intraday plan adjustment. The carbon saving capacity is calculated using the sixth calculation formula, and the equipment output is adjusted in real time according to the maximum carbon saving capacity: Finally, the sixth calculation formula TJ=S15÷XQ15 is used to calculate the carbon saving capacity. Among them, TJ represents the carbon saving capacity, S15 represents the total power generation of new energy within 15 minutes, and XQ15 represents the power supply demand circuit within 15 minutes. Based on the calculated carbon-saving capacity, the equipment output can be adjusted in real time to maximize the goal of energy conservation and emission reduction.

[0145] Figure 7 It is a flowchart of updating the power generation plan with real-time data according to the layer-by-layer optimization results in a method for generating a multi-level power generation plan for the day-ahead, intra-day and real-time according to an embodiment of the present invention.

[0146] like Figure 7 As shown, in one or more embodiments, preferably, the real-time data updating of the power generation plan according to the layer-by-layer optimization results specifically includes:

[0147] S701, obtaining optimized day-ahead, intra-day and real-time sub-plans;

[0148] S702, respectively updating the intra-day sub-plan and the day-ahead sub-plan;

[0149] S703. Dynamically execute the real-time sub-plan.

[0150] In an embodiment of the present invention, the optimized day-ahead, intraday and real-time sub-plans are obtained: first, the day-ahead, intraday and real-time sub-plans are obtained from the preset optimization algorithm after layer-by-layer optimization. These sub-plans have been adjusted and optimized according to the first to sixth calculation formulas. The intraday sub-plan and the day-ahead sub-plan are updated respectively: next, the optimized day-ahead sub-plan and the intraday sub-plan are updated to the corresponding plans respectively. This means that the optimized plan needs to replace the original plan to ensure that the power system operates according to the latest optimization results. The real-time sub-plan is dynamically executed: finally, the real-time sub-plan is dynamically executed. Since the real-time sub-plan is generated based on real-time data, it needs to be dynamically adjusted according to the real-time power grid status and load demand. A real-time data acquisition system can be set up to collect real-time data of the power grid in a period of 5-15 minutes, and the real-time sub-plan is dynamically adjusted according to these data.

[0151] According to a second aspect of an embodiment of the present invention, a day-ahead, intra-day and real-time multi-level power generation plan generation system is provided.

[0152] Figure 8 It is a structural diagram of a system for generating a multi-level power generation plan for the day-ahead, intra-day and real-time according to an embodiment of the present invention.

[0153] In one or more embodiments, preferably, the day-ahead, intra-day and real-time multi-level power generation plan generation system includes:

[0154] The data collection module 801 is used to obtain historical load data and collect the current power generation plan in real time;

[0155] The load forecasting module 802 is used to establish an analytical mathematical model including the characteristics of the generator set, the grid structure and the market demand;

[0156] Mathematical modeling module 803, used to establish a mapping model of power generation and loss in the entire system;

[0157] The hierarchical optimization module 804 is used to decompose the original power generation plan into three sub-plans: day-ahead, intra-day and real-time by adopting a hierarchical decomposition method;

[0158] Genetic algorithm module 805, used to set a preset optimization algorithm to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer;

[0159] The dynamic adjustment module 806 is used to update the power generation plan in real time based on the optimization results layer by layer.

[0160] In the embodiment of the present invention, a system suitable for different structures is realized through a series of modular designs. The system can achieve closed-loop, reliable and efficient execution through collection, analysis and control.

[0161] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0162] According to a fourth aspect of an embodiment of the present invention, an electronic device is provided. Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. Fig. 9 The electronic device shown is a general day-ahead, intraday and real-time multi-level power generation plan generation device. The electronic device can be a smart phone, tablet computer and other devices. As shown, the electronic device 900 includes a processor 901 and a memory 902. Among them, the processor 901 is electrically connected to the memory 902. The processor 901 is the control center of the terminal 900, which uses various interfaces and lines to connect various parts of the entire terminal, executes various functions of the terminal and processes data by running or calling computer programs stored in the memory 902, and calling data stored in the memory 902, so as to monitor the terminal as a whole.

[0163] In this embodiment, the processor 901 in the electronic device 900 will load the instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and the processor 901 will run the computer program stored in the memory 902 to achieve various functions: obtain historical load data and collect the current power generation plan in real time; establish an analytical mathematical model including the characteristics of the generator set, the grid structure and the market demand; establish a mapping model of power generation and loss in the entire system; use a hierarchical decomposition method to decompose the original power generation plan into three sub-plans: day-ahead, intra-day and real-time; set a preset optimization algorithm to optimize the three sub-plans layer by layer; and update the power generation plan with real-time data according to the optimization results layer by layer.

[0164] The memory 902 may be used to store computer programs and data. The computer programs stored in the memory 902 include instructions that can be executed in the processor. The computer programs may constitute various functional modules. The processor 901 executes various functional applications and data processing by calling the computer programs stored in the memory 902.

[0165] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0166] In the solution of the present invention, the problem is decomposed into three sub-problems: day-ahead, intra-day and real-time, and solved separately. This strategy can reduce the complexity of the problem, making each sub-problem easier to handle, while ensuring the optimality and feasibility of the overall solution.

[0167] In the solution of the present invention, the optimal solution is automatically found for each sub-problem, which is suitable for solving multi-objective and multi-constraint optimization problems.

[0168] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0169] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0172] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for generating multi-level power generation plans on a day-ahead, intra-day and real-time basis, characterized in that: The method includes: Obtain historical load data and collect current power generation plans in real time; Establish analytical mathematical models that include generator characteristics, grid structure, and market demand; Establish a mapping model of power generation and loss in the entire system; The original power generation plan is decomposed into three sub-plans: day-ahead, intra-day and real-time. Set the preset optimization algorithm to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer; Based on the optimization results layer by layer, the power generation plan is updated with real-time data.

2. The method for generating a multi-level power generation plan for the day before, within the day and in real time as claimed in claim 1, characterized in that: The acquisition of historical load data and real-time collection of current power generation plans specifically include: Extract historical load data from energy management systems or distribution automation systems; Clean and preprocess the collected historical data to remove outliers or incomplete records to ensure data quality and consistency; Configure a real-time data acquisition system to obtain current generation plans and real-time load data from the power plant's control system or market operation center.

3. The method for generating a day-ahead, intra-day and real-time multi-level power generation plan according to claim 1, characterized in that: The establishment of an analytical mathematical model including the characteristics of the generator set, the grid structure and the market demand specifically includes: According to the type of generator set, a corresponding analytical mathematical model is established to describe its operating characteristics; Build analytical mathematical models of the power grid and determine market demand.

4. The method for generating a multi-level power generation plan for the day before, within the day and in real time as claimed in claim 1, characterized in that: The establishment of a mapping model of power generation and loss in the entire system specifically includes: Analyze each core device according to the analytical mathematical model to determine the relationship between its loss and output power; The mapping relationship between the loss and the emitted power is set as a mapping model.

5. The method for generating a multi-level power generation plan for the day before, within the day and in real time as claimed in claim 1, characterized in that: The original power generation plan is decomposed into three sub-plans: day-ahead, intra-day and real-time by adopting a layered decomposition method, which specifically includes: Get the original power generation plan, first split the day-ahead plan, and obtain the part of the current power generation plan that has been determined the day before as the day-ahead power generation plan component; Get the original power generation plan and determine the new adjustments generated within the current day as the incoming plan component; Based on the real-time voltage trading volume of 5-15 minutes, the latest power generation plan changes formed in real time are set as real-time plans.

6. The method for generating a multi-level power generation plan for the day before, within the day and in real time as claimed in claim 1, characterized in that: The preset optimization algorithm is set to optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer, specifically including: After obtaining the day-ahead sub-plan, the first calculation formula is used to calculate the imbalance between the day-ahead plan and the model; Determine whether the second calculation formula is satisfied, and then use the third calculation formula to generate the intraday adjustment basis; After obtaining the intra-day sub-plan, the power output of the adjusted intra-day plan is generated using the fourth calculation formula; According to the power output of the adjusted intraday plan, using the mathematical model of power generation and loss, it is determined whether the fifth calculation formula is satisfied. If not, the preset demand is satisfied by adjusting the intraday plan; The carbon saving capacity is calculated using the sixth calculation formula, and the output of the equipment is adjusted in real time according to the maximum carbon saving capacity; The first calculation formula is: Among them, BJ is the imbalance between the day-ahead plan and the model, Pi is the loss estimation deviation of the i-th node under the day-ahead plan, and n is the total number of nodes; The second calculation formula is: BJ>Y Where, Y is the mismatch contrast margin; The third calculation formula is: J=KT-PC Among them, J is the intraday adjustment benchmark, KT is the adjustable power demand, PC is the loss deviation and; The fourth calculation formula is: Th=tq+J Among them, th is the power output of the adjusted intraday plan, and tq is the power output of the intraday sub-plan; The fifth calculation formula is: SZ <Y4 GXD>Y5 Among them, SZ is the total loss, GXD is the power demand responsiveness, Y4 is the loss limit margin, and Y5 is the response speed margin; The sixth calculation formula is: TJ=S15÷XQ15 Among them, TJ is the carbon saving capacity, S15 is the total power generation of new energy within 15 minutes, and XQ15 is the power supply demand circuit within 15 minutes.

7. The method for generating a multi-level power generation plan for the day before, within the day and in real time as claimed in claim 1, characterized in that: The real-time data updating of the power generation plan based on the layer-by-layer optimization results specifically includes: Get the optimized day-ahead, intraday, and real-time sub-plans; Update the intraday sub-plan and the day-ahead sub-plan separately; Dynamic execution of real-time sub-plans.

8. A multi-level power generation plan generation system for day-ahead, intra-day and real-time, characterized in that: The system is used to implement the method according to any one of claims 1 to 7, and the system comprises: Data collection module, used to obtain historical load data and collect current power generation plans in real time; Load forecasting module, used to establish analytical mathematical models that include generator characteristics, grid structure and market demand; Mathematical modeling module, used to establish a mapping model of power generation and loss in the entire system; The hierarchical optimization module is used to decompose the original power generation plan into three sub-plans: day-ahead, intraday and real-time. The genetic algorithm module is used to set the preset optimization algorithm and optimize the three sub-plans of day-ahead, intra-day and real-time layer by layer; The dynamic adjustment module is used to update the power generation plan based on the layer-by-layer optimization results and real-time data.

9. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 7 when executed by a processor.

10. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-7.

Images