Renewable energy consumption coordination method based on artificial intelligence
Through the renewable energy consumption coordination method based on artificial intelligence, the neural network and support vector machine model are used to analyze the renewable energy consumption capacity of large power grids, and the problems of low analysis accuracy and difficulty in coordination in the existing methods are solved, achieving high accuracy Renewable energy consumption coordination and cost optimization.
Patent Information
- Application Number
- CN202411511890.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2025-02-18
AI Technical Summary
The current method of evaluating renewable energy consumption capacity of large power grids is too simple and lacks standardized information processing and modeling capabilities, resulting in low analysis accuracy of renewable energy consumption capacity and difficulty in coordination.
Using the renewable energy consumption coordination method based on artificial intelligence, the parameters to be coordinated are obtained and input into the pre-established renewable energy consumption coordination model, and the neural network and support vector machine model are used for analysis, and constraints and target functions are added. To coordinate the consumption of renewable energy.
The analysis accuracy of the renewable energy consumption capacity of large power grids has been improved, the problem of difficulty in coordinating the consumption capacity of renewable energy has been solved, and the output of new energy and the cost of peak shaving is minimized.
Smart Images
Figure CN119482710A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power data analysis, and in particular to a renewable energy consumption coordination method based on artificial intelligence. Background Art
[0002] In the face of growing demand for clean energy and pressure to reduce carbon emissions, energy and power development will also face severe challenges. With the implementation of clean alternative technology paths, the pressure to absorb renewable energy will become more prominent, and the nature of energy security issues and the pattern of the power system will undergo new changes.
[0003] The current large-scale power grid renewable energy absorption capacity assessment method is too simple, lacks standardized information processing and modeling capabilities, and conducts separate analysis and estimation of wind power, photovoltaic and other generating units, resulting in low accuracy in the analysis of large-scale power grid renewable energy absorption capacity and difficulty in coordinating renewable energy absorption capacity. Summary of the invention
[0004] In view of this, the purpose of the present invention is to provide a renewable energy consumption coordination method based on artificial intelligence to overcome the current problems of low analysis accuracy of the renewable capacity consumption capacity of large power grids and difficulty in coordinating the renewable capacity consumption capacity due to separate analysis and estimation of wind power, photovoltaic and other power generation units.
[0005] To achieve the above objectives, the present invention adopts the following technical solutions:
[0006] A renewable energy consumption coordination method based on artificial intelligence, comprising:
[0007] Obtain parameters to be coordinated; the coordination parameters include: output parameters of renewable energy units, power generation flow parameters of hydropower stations, water balance parameters of hydropower stations, reservoir capacity parameters of hydropower stations, output parameters of thermal power units, state variable parameters of thermal power units, start-up and shutdown variable parameters of thermal power units, minimum start-up time parameters of thermal power units, minimum shutdown time parameters of thermal power units, line transmission capacity parameters, peak load parameters of thermal power units, and power parameters of thermal power units;
[0008] Inputting the parameters to be coordinated into a pre-established renewable energy consumption coordination model;
[0009] Obtaining the results of the renewable energy consumption coordination model;
[0010] Coordinate the consumption of renewable energy sources based on the results.
[0011] Furthermore, in the method described above, the results of the renewable energy consumption coordination model include: maximizing the output of new energy and minimizing the peak-shaving costs.
[0012] Furthermore, in the above method, the pre-established renewable energy consumption coordination model includes:
[0013] Establishing the renewable energy consumption coordination model through a neural network back propagation model and a support vector machine model;
[0014] Add constraints and objective functions to the renewable energy consumption coordination model.
[0015] Furthermore, in the above method, the constraints of the renewable energy consumption coordination model include:
[0016] Renewable energy unit output constraints, hydropower station power generation flow constraints, hydropower station water balance constraints and hydropower station reservoir capacity constraints.
[0017] Furthermore, in the method described above, the constraints of the renewable energy consumption coordination model also include: output constraints of thermal power units, state variables and start-up and shutdown variable constraints of thermal power units, minimum start-up and shutdown time constraints of thermal power units, system positive and negative standby, system load balance constraints, line transmission capacity constraints, thermal power unit peak regulation constraints and thermal power unit power constraints.
[0018] Furthermore, in the method described above, the objective function of the renewable energy consumption coordination model includes: maximizing the new energy output function and minimizing the peak-shaving cost function.
[0019] Furthermore, in the above method, the output constraint of the renewable energy unit is: and in, They are the minimum output of photovoltaic unit i at time t, the maximum output of photovoltaic unit i at time t, the minimum output of wind turbine unit i at time t, the maximum output of wind turbine unit i at time t, the minimum output of hydropower unit i at time t and the maximum output of hydropower unit i at time t;
[0020] The power generation flow constraint of the hydropower station is: in, are the lower and upper limits of the power generation flow of unit i at time t, respectively. The relationship between the power generation flow of the hydropower station and the hydropower output can be expressed as: H i，t =α i q i，t , where α i It is the conversion coefficient between the power generation flow and output of the hydropower station;
[0021] The water balance constraint of the hydropower station is: Where V i，t is the reservoir volume of hydropower station i at time t, are the inflow, power generation and other flows of hydropower unit i at time t;
[0022] The storage capacity constraint of the hydropower station is: in are the lower and upper limits of the storage capacity of reservoir i at time t.
[0023] Furthermore, in the method described above, the output constraint of the thermal power unit is: where v i，t The state variables of unit i at time t are: G i，t They represent the lower limit, upper limit and output of thermal power unit i at time t respectively;
[0024] The state variables and start-up and shutdown variables of the thermal power unit are constrained as follows: i，t -v i，t-1 =x i，t -y i，t and x i，t +y i，t ≤1, where x i，t ,y i，t They represent the startup integer variable and shutdown integer variable of thermal power unit i at time t respectively;
[0025] The minimum start-stop time constraint of the thermal power unit is: and Among them, M U , M D are the minimum start-up time and minimum shutdown time of thermal power unit i respectively;
[0026] The positive and negative standby of the system are: and Load t , P.R. t , NR t They represent the system load, positive reserve and negative reserve at time t respectively;
[0027] The system load balancing constraints are:
[0028] The line transmission capacity constraint is: in P i，j They represent the transmission limit and the transmitted active power of branch i and j respectively;
[0029] The peak load regulation constraint of the thermal power unit is: where g i，k It represents the peak load of the kth thermal power unit i, Represents the lower limit of peak load regulation of thermal power unit i at time t;
[0030] The power consumption constraint of the thermal power unit is: in It represents the lower and upper limits of the power required by the Ith thermal power unit set, ΔT represents the time interval, slack_lb I , slack_ub I is a slack variable.
[0031] Furthermore, in the method described above, the function for maximizing the output of new energy is:
[0032] Furthermore, in the above method, the function for minimizing the peak load cost is: where c i，k It represents the peak load quotation of the kth section of unit i.
[0033] Furthermore, the above method further includes:
[0034] Get historical data;
[0035] The renewable energy consumption coordination model is trained according to the historical data.
[0036] Furthermore, the method described above, before training the renewable energy consumption coordination model according to the historical data, further includes:
[0037] Adjust the credibility of the historical data through correction and correlation methods, and detect bad data in the historical data;
[0038] The bad data is deleted.
[0039] The beneficial effects of the present invention are:
[0040] This application first obtains the parameters to be coordinated; the coordination parameters include: output parameters of renewable energy units, power generation flow parameters of hydropower stations, water balance parameters of hydropower stations, reservoir parameters of hydropower stations, output parameters of thermal power units, state variable parameters of thermal power units, start-up and shutdown variable parameters of thermal power units, minimum start-up time parameters of thermal power units, minimum shutdown time parameters of thermal power units, line transmission capacity parameters, peak load parameters of thermal power units and power parameters of thermal power units, and inputs the parameters to be coordinated into the pre-established renewable energy consumption coordination model to obtain the results of the renewable energy consumption coordination model, and coordinate the consumption of renewable energy according to the results. By comprehensively analyzing the renewable energy consumption capacity of the large power grid through the comprehensive analysis of multiple parameters of renewable energy generators and other generators, the analysis accuracy of the renewable energy consumption capacity of the large power grid is improved, and the problem of difficulty in coordinating the renewable energy consumption capacity is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 It is a flow chart provided by an embodiment of a renewable energy consumption coordination method based on artificial intelligence of the present invention. DETAILED DESCRIPTION
[0043] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.
[0044] The current large-scale power grid renewable energy absorption capacity assessment method is too simple, lacks standardized information processing and modeling capabilities, and conducts separate analysis and estimation of wind power, photovoltaic and other generating units, resulting in low accuracy in the analysis of large-scale power grid renewable energy absorption capacity and difficulty in coordinating renewable energy absorption capacity.
[0045] Figure 1 This is a flowchart provided by an embodiment of a renewable energy consumption coordination method based on artificial intelligence of the present invention. Figure 1 , this embodiment may include the following steps:
[0046] S1. Obtain parameters to be coordinated; the coordination parameters include: output parameters of renewable energy units, power generation flow parameters of hydropower stations, water balance parameters of hydropower stations, reservoir capacity parameters of hydropower stations, output parameters of thermal power units, state variable parameters of thermal power units, start-up and shutdown variable parameters of thermal power units, minimum start-up time parameters of thermal power units, minimum shutdown time parameters of thermal power units, line transmission capacity parameters, peak load parameters of thermal power units and power parameters of thermal power units.
[0047] S2. Input the parameters to be coordinated into the pre-established renewable energy consumption coordination model
[0048] S3. Obtain the results of the renewable energy consumption coordination model
[0049] S4. Coordinate the consumption of renewable energy based on the results.
[0050] It can be understood that the present embodiment first obtains the parameters to be coordinated; the coordination parameters include: the output parameters of the renewable energy units, the power generation flow parameters of the hydropower station, the water balance parameters of the hydropower station, the reservoir parameters of the hydropower station, the output parameters of the thermal power units, the state variable parameters of the thermal power units, the start-up and shutdown variable parameters of the thermal power units, the minimum start-up time parameters of the thermal power units, the minimum shutdown time parameters of the thermal power units, the line transmission capacity parameters, the peak load parameters of the thermal power units and the power parameters of the thermal power units, and the parameters to be coordinated are input into the pre-established renewable energy consumption coordination model to obtain the results of the renewable energy consumption coordination model, and the consumption of renewable energy is coordinated according to the results. By comprehensively analyzing the renewable energy consumption capacity of the large power grid through the various parameters of the renewable energy generators and other generators, the analysis accuracy of the renewable energy consumption capacity of the large power grid is improved, and the problem of the difficulty in coordinating the renewable energy consumption capacity is solved.
[0051] Preferably, the results of the renewable energy consumption coordination model include: maximizing the output of new energy and minimizing the peak-shaving costs.
[0052] Preferably, the pre-established renewable energy consumption coordination model includes:
[0053] A renewable energy consumption coordination model is established through the back propagation model of neural network and support vector machine model;
[0054] Add constraints and objective functions to the renewable energy consumption coordination model.
[0055] It is understandable that the renewable energy consumption coordination model mainly adopts the back propagation model of neural network and the support vector machine model. After repeated experiments, we mixed the above two models according to a certain algorithm as a new model. The renewable energy consumption calculation is based on the system load forecast, bus load forecast, tie line plan, unit status as the boundary, and the future grid model topology. It constructs a mixed integer (MIP) optimization model with the goal of maximizing the consumption of renewable energy, taking into account load balance, system positive and negative standby, unit climbing, grid safety and other constraints. It uses branch and bound, cutting plane, model decomposition and other technologies to obtain the maximum amount of renewable energy and wind power that can be absorbed by the system under the changed boundary.
[0056] Preferably, the constraints of the renewable energy consumption coordination model include:
[0057] Renewable energy unit output constraints, hydropower station power generation flow constraints, hydropower station water balance constraints, hydropower station reservoir capacity constraints, thermal power unit output constraints, thermal power unit state variables and start-up and shutdown variable constraints, thermal power unit minimum start-up and shutdown time constraints, system positive and negative standby, system load balance constraints, line transmission capacity constraints, thermal power unit peak load constraints and thermal power unit power constraints.
[0058] Preferably, the objective function of the renewable energy consumption coordination model includes: maximizing the new energy output function and minimizing the peak load cost function.
[0059] It is understandable that by adding constraints to the renewable energy consumption coordination model, the operating conditions simulated by the model are made as close to the actual conditions as possible, and the final result is obtained by adding an objective function to the model. In this embodiment, by maximizing the new energy output function and minimizing the peak-shaving cost function, the maximum new energy output and the minimum peak-shaving cost after comprehensive analysis of the power grid are obtained; then, according to the maximum new energy output and the minimum peak-shaving cost of the power grid, the actual power grid is adjusted to coordinate the renewable energy consumption capacity of the power grid.
[0060] Preferably, the output constraint of the renewable energy generating unit is: and in, They are the minimum output of photovoltaic unit i at time t, the maximum output of photovoltaic unit i at time t, the minimum output of wind turbine unit i at time t, the maximum output of wind turbine unit i at time t, the minimum output of hydropower unit i at time t and the maximum output of hydropower unit i at time t; it should be noted that when photovoltaic and wind power are fully absorbed
[0061] The power generation flow constraint of the hydropower station is: in, are the lower and upper limits of the power generation flow of unit i at time t, respectively. The relationship between the power generation flow of the hydropower station and the hydropower output can be expressed as: H i，t =α i q i，t , where α i It is the conversion coefficient between the power generation flow and output of the hydropower station;
[0062] The water balance constraint of the hydropower station is: Where V i，t is the reservoir volume of hydropower station i at time t, Q i，t ,q i，t , are the inflow, power generation and other flows of hydropower unit i at time t; other flows include irrigation water, domestic water and abandoned water;
[0063] The storage capacity constraint of the hydropower station is: in are the lower and upper limits of the storage capacity of reservoir i at time t;
[0064] The output constraints of thermal power units are: , where v i，tThe state variable of unit i at time t is an integer variable with values of 0 and 1. 0 means the unit is not online (shutdown or maintenance), and 1 means it is online. G i，t They represent the lower limit, upper limit and output of thermal power unit i at time t respectively;
[0065] The state variables and start-up and shutdown variables of the thermal power unit are constrained as follows: i，t -v i，t-1 =x i，t -y i，t and x i，t +y i，t ≤1, where x i，t ,y i，t They represent the startup integer variable and shutdown integer variable of thermal power unit i at time t respectively;
[0066] The minimum start-up and shutdown time constraints of thermal power units are: and , where M U , M D are the minimum start-up time and minimum shutdown time of thermal power unit i respectively;
[0067] The system positive and negative backup are: and Load t , P.R. t , NR t They represent the system load, positive reserve and negative reserve at time t respectively;
[0068] The system load balancing constraints are:
[0069] The line transmission capacity constraint is: in P i，j They represent the transmission limit and the transmitted active power of branch i and j respectively;
[0070] The peak load constraints of thermal power units are: where g i，k It represents the peak load of the kth thermal power unit i, Represents the lower limit of peak load regulation of thermal power unit i at time t;
[0071] The power consumption constraint of thermal power units is: in It represents the lower and upper limits of the power required by the Ith thermal power unit set, ΔT represents the time interval, slack_lb I , slack_ub I is a slack variable. In some optional embodiments, slack_lb I, slack_ub I It is a slack variable set to prevent the set of units from failing to meet the power requirements.
[0072] Preferably, the function for maximizing the output of new energy is:
[0073] The function to minimize the peak load cost is: where c i，k It represents the peak load quotation of the kth section of unit i.
[0074] Preferably, it also includes:
[0075] Get historical data;
[0076] Train a renewable energy consumption coordination model based on historical data.
[0077] Preferably, before training the renewable energy consumption coordination model according to historical data, the method further includes:
[0078] Adjust the credibility of historical data through correction and correlation methods, and detect bad data in historical data;
[0079] Delete bad data.
[0080] It is understandable that in order to obtain a better prediction effect, the renewable energy consumption coordination model is trained through historical data. At the same time, in order to ensure the correctness of the output results of the renewable energy consumption coordination model, the rationality of the historical data used for prediction should be fully guaranteed. In this embodiment, before training the renewable energy consumption coordination model, the credibility of the historical data is adjusted by the correction method and the correlation method, and the bad data in the historical data is detected and deleted, so as to ensure the rationality of the historical data.
[0081] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.
[0082] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.
[0083] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.
[0084] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0085] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0086] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0087] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.
[0088] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0089] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A renewable energy consumption coordination method based on artificial intelligence, characterized in that: include: Get the parameters to be coordinated; The coordination parameters include: output parameters of renewable energy units, power generation flow parameters of hydropower stations, water balance parameters of hydropower stations, reservoir capacity parameters of hydropower stations, output parameters of thermal power units, state variable parameters of thermal power units, start-up and shutdown variable parameters of thermal power units, minimum start-up time parameters of thermal power units, minimum shutdown time parameters of thermal power units, line transmission capacity parameters, peak load parameters of thermal power units and power parameters of thermal power units; Inputting the parameters to be coordinated into a pre-established renewable energy consumption coordination model; Obtaining the results of the renewable energy consumption coordination model; Coordinate the consumption of renewable energy sources based on the results.
2. The method according to claim 1, characterized in that: The results of the renewable energy consumption coordination model include: maximizing the output of new energy and minimizing the peak-shaving costs.
3. The method according to claim 2, characterized in that The pre-established renewable energy consumption coordination model includes: Establishing the renewable energy consumption coordination model through a neural network back propagation model and a support vector machine model; Add constraints and objective functions to the renewable energy consumption coordination model.
4. The method according to claim 3, characterized in that The constraints of the renewable energy consumption coordination model include: Renewable energy unit output constraints, hydropower station power generation flow constraints, hydropower station water balance constraints and hydropower station reservoir capacity constraints.
5. The method according to claim 4, characterized in that The constraints of the renewable energy consumption coordination model also include: Output constraints of thermal power units, state variables and start-up and shutdown variables constraints of thermal power units, minimum start-up and shutdown time constraints of thermal power units, system positive and negative standby, system load balance constraints, line transmission capacity constraints, peak load regulation constraints of thermal power units and power constraints of thermal power units.
6. The method according to claim 5, characterized in that The objective function of the renewable energy consumption coordination model includes: maximizing the new energy output function and minimizing the peak load cost function.
7. The method according to claim 6, characterized in that The output constraint of the renewable energy unit is: and in, They are the minimum output of photovoltaic unit i at time t, the maximum output of photovoltaic unit i at time t, the minimum output of wind turbine unit i at time t, the maximum output of wind turbine unit i at time t, the minimum output of hydropower unit i at time t and the maximum output of hydropower unit i at time t; The power generation flow constraint of the hydropower station is: in, are the lower and upper limits of the power generation flow of unit i at time t, respectively. The relationship between the power generation flow of the hydropower station and the hydropower output can be expressed as: H i，t =α i q i，t , where α i It is the conversion coefficient between the power generation flow and output of the hydropower station; The water balance constraint of the hydropower station is: Where V i，t is the reservoir volume of hydropower station i at time t, are the inflow, power generation and other flows of hydropower unit i at time t; The storage capacity constraint of the hydropower station is: in are the lower and upper limits of the storage capacity of reservoir i at time t.
8. The method according to claim 7, characterized in that The output constraint of the thermal power unit is: where υ i，t The state variables of unit i at time t are: G i，t They represent the lower limit, upper limit and output of thermal power unit i at time t respectively; The state variables and start-up and shutdown variables of the thermal power unit are constrained as follows: i，t -υ i，t-1 =x i，t -y i，t and x i，t +y i，t ≤1, where x i，t ,y i，t They represent the startup integer variable and shutdown integer variable of thermal power unit i at time t respectively; The minimum start-stop time constraint of the thermal power unit is: and Among them, M U , M D are the minimum start-up time and minimum shutdown time of thermal power unit i respectively; The positive and negative standby of the system are: and Load t , P.R. t , NR t They represent the system load, positive reserve and negative reserve at time t respectively; The system load balancing constraints are: The line transmission capacity constraint is: in They represent the transmission limit and the transmitted active power of branch i and j respectively; The peak load regulation constraint of the thermal power unit is: where g i，k It represents the peak load of the kth thermal power unit i, Represents the lower limit of peak load regulation of thermal power unit i at time t; The power consumption constraint of the thermal power unit is: in It represents the lower and upper limits of the power required by the Ith thermal power unit set, ΔT represents the time interval, slack_lb I , slack_ub I is a slack variable.
9. The method according to claim 8, characterized in that The function for maximizing the output of new energy is:
10. The method according to claim 9, characterized in that The function for minimizing the peak load cost is: where c i，k It represents the peak load quotation of the kth section of unit i.
11. The method according to claim 3, characterized in that Also includes: Get historical data; The renewable energy consumption coordination model is trained according to the historical data.
12. The method according to claim 11, characterized in that Before training the renewable energy consumption coordination model according to the historical data, the method further includes: Adjust the credibility of the historical data through correction and correlation methods, and detect bad data in the historical data; The bad data is deleted.