New energy optimal installed capacity prediction method and system
Through the risk assessment index model based on the penetration rate of new energy installed capacity, the problem of insufficient impact assessment of new energy installed capacity prediction on the power system in the existing technology is solved, and the optimal new energy installed capacity is achieved Predict and safe balanced operation of the power system.
Patent Information
- Application Number
- CN202410620592.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-20
- Publication Date
- 2024-11-12
AI Technical Summary
The existing new energy installed capacity prediction method fails to effectively evaluate the impact of new energy installed capacity on the three parties in the power system, and lacks prediction methods from the optimal perspective, resulting in power system balance and risks. Inadequate assessment.
Using a risk assessment index model based on the penetration rate of new energy installed capacity, the optimal predictive value of new energy installed capacity is calculated through the safety constraint economic scheduling model and the risk assessment index model, and comprehensively consider the risks and risks of the three parties, namely, the network and the Dutch. Benefits, generate comprehensive risk assessment indicator curves to determine the optimal installed capacity.
It has achieved the optimal prediction of new energy installed capacity, improved the safe and balanced operation of the power system, helped power companies and new energy manufacturers to identify market risks, reasonably allocate resources and production capacity, and ensure win-win and balanced three parties.
Smart Images

Figure CN118940875A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of system installed capacity prediction, and in particular to a method and system for predicting optimal installed capacity of new energy. Background Art
[0002] New energy power represented by wind and solar energy has gradually become the most promising power generation method of renewable energy with its advantages of low pollution, no energy consumption, and renewability. The proportion of new energy installed capacity in the power system has increased year by year. However, due to the inherent randomness and volatility of new energy, the power system's ability to accept new energy is limited by multiple factors such as load and grid. Wind and solar power are limited by the flexibility of power system operation. Therefore, when the proportion of new energy installed capacity increases and power supply exceeds load demand, in order to ensure the real-time balance of the power system, the problem of limited new energy consumption will arise. How to balance power supply and new energy consumption in the power system, and how to balance the risks and interests of the three parties of "source, network, and load" in the context of the power market, scientifically plan the installed capacity of new energy and ensure the balanced and safe operation of the power system is of great significance.
[0003] The existing forecasting methods for installed capacity of new energy sources mainly analyze the historical data of installed capacity of new energy sources and related influencing factors, and use certain mathematical methods to forecast the installed capacity of new energy sources in the future. The forecast of installed capacity of new energy sources can be mainly divided into the following four categories:
[0004] (1) Forecast based on exponentially weighted average method
[0005] The exponential weighted average method is to decompose the original sequence, separate the trend sequence, cycle sequence and level sequence from the original sequence, so as to decompose the complex volatile sequence into several relatively smooth sequences, and then make corresponding predictions for the decomposed sequence. The prediction characteristics based on the exponential weighted average method are as follows: 1) Concise calculation steps: The prediction model based on the exponential weighted average method has concise calculation steps and can achieve high prediction accuracy for medium and long-term predictions; 2) Narrow application areas: The prediction model based on the exponential weighted average method can only achieve high-precision predictions in a small number of prediction areas. There are two reasons for this: First, the parameter determination method of the exponential weighted average method is relatively subjective; second, the method lacks generalizability due to the limitation of the model structure.
[0006] (2) Regression-based prediction method
[0007] The regression-based forecasting method is a widely used method at this stage. Its main modeling idea is to establish a regression equation by analyzing the inherent laws of historical data of wind power installed capacity or the influence of different influencing factors on wind power installed capacity, and then predict the future wind power installed capacity through the regression equation. The main features of the regression-based forecasting method include: 1) High data dimension requirements: Predicting wind power installed capacity requires a relatively large amount of data. In addition, if multivariate indicator modeling is performed, the data collection requirements are even higher; 2) The computational cost is relatively high. Since the regression method requires a higher data dimension, the accompanying computational cost is also higher.
[0008] (3) Prediction based on grey prediction model
[0009] The grey prediction model is a prediction model based on the grey system theory. Its principle is to achieve data fitting and then make predictions by constructing grey differential equations. The characteristics of the grey prediction model are as follows: 1) Applicable to small sample problems: The prediction method based on the grey prediction model is applicable to prediction problems with poor data and small samples. It cannot make predictions for short-term predictions with too much data; 2) The prediction process is reproducible: The solution principle of the grey prediction model is achieved by solving differential equations. Its prediction process and prediction results can be reproduced, which is convenient for prediction based on the grey prediction model. The grey prediction model is a prediction model based on the grey system theory. Its principle is to achieve data fitting and then make predictions by constructing grey differential equations.
[0010] (4) Machine Learning Methods
[0011] The prediction models established based on machine learning methods mainly include artificial neural networks, extreme learning machines and other methods. These methods mainly train the models by simulating various processes. For example, neural networks simulate the data processing process of human neurons to establish models, and then predict the data through models. At present, the prediction model based on machine learning is the most widely studied model by scholars, because machine learning methods have the following characteristics: 1) Good model fitting ability: The artificial neural network model has a low dependence on the data type, and has good fitting performance for both linear data and nonlinear data, and can achieve ultra-high prediction accuracy; 2) Excellent model generalization performance: The accuracy of the artificial neural network prediction model can achieve efficient prediction on different data sets, meeting the prediction requirements of practical applications; 3) Large data demand: The machine learning model has a relatively large demand for data volume. If the data volume is not enough to meet the data requirements of the machine learning model, the problem of underfitting will occur, making the model unable to achieve high-precision prediction; 4) It is more suitable for ultra-short-term or short-term predictions, such as short-term wind speed prediction, short-term wind power output prediction, and for medium- and long-term predictions, due to the relatively scarce data volume, it cannot meet its requirements for high sample capacity.
[0012] At present, for the prediction method of renewable energy installed capacity including wind and solar power, most of the research at home and abroad predicts the renewable energy installed capacity in the future based on the historical data of renewable energy installed capacity and related meteorological factors. There is no risk assessment model and method to vertically evaluate the impact of different renewable energy installed capacity on the "source, network and load" in the power system. There is no method to predict the renewable energy installed capacity from the optimal perspective, and there is no method to predict the optimal installed capacity of renewable energy. Summary of the invention
[0013] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art and provide a method and system for predicting the optimal installed capacity of new energy so as to achieve the optimal prediction of the installed capacity of new energy while ensuring the safe and balanced operation of the power system.
[0014] To achieve the above object, the technical solution of the present invention is:
[0015] In a first aspect, the present invention provides a method for predicting optimal installed capacity of new energy, the method comprising:
[0016] Input the parameters of the regional power system to be predicted and give the initial values of the power system-level decision variables, pass them to the security-constrained economic dispatch model for solution, and calculate the node electricity price at each time under the current new energy installed capacity penetration rate;
[0017] The node electricity price at each moment under the current penetration rate of new energy installed capacity is calculated as the input of the risk assessment index model, and the risk index values of the three parties, namely, the new energy developer side, the user side and the power grid side, are calculated through the risk assessment index model;
[0018] Using the risk index value as an input of a comprehensive risk assessment index calculation model to obtain a comprehensive risk assessment index value under the current permeability;
[0019] The installed capacity of new energy is changed according to the set penetration rate increment, and the installed capacity of conventional units is changed proportionally. The calculation is brought into the safety constrained economic dispatch model. If the upper limit kmax set for the installed capacity penetration rate of new energy is reached, the calculation is completed, and the comprehensive risk assessment index value corresponding to each penetration rate k is output to generate a comprehensive risk assessment index curve with the independent variable being the installed capacity penetration rate k of new energy and the dependent variable being the comprehensive risk assessment index. Among them, the installed capacity penetration rate corresponding to the lowest point of the comprehensive risk assessment index curve is the optimal installed capacity penetration rate of new energy, corresponding to the optimal installed capacity of new energy.
[0020] In a second aspect, the present invention provides a new energy optimal installed capacity prediction system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0021] In a third aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above are implemented.
[0022] Compared with the prior art, the present invention has the following beneficial effects:
[0023] The method of the present invention adopts the optimization idea and proposes a new energy optimal installed capacity prediction method based on the new energy installed capacity penetration rate risk assessment index model, which realizes the optimal prediction of new energy installed capacity. In the power market environment, it can help power companies and users improve market risk identification and assessment, provide decision-making references for installed capacity for new energy manufacturers, and help new energy manufacturers to reasonably allocate relevant resources and production capacity. Compared with the traditional installed capacity prediction, the prediction method of the present invention can comprehensively consider the risks and interests of the source, the network, and the load, and predict the new energy installed capacity that is win-win and balanced for the three parties from the optimal perspective, realizing a scientific and reasonable risk assessment of different new energy installed capacity penetration rates, so as to ensure the safe and balanced operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 A flowchart of a method for predicting optimal installed capacity of new energy provided in Example 1 of the present invention;
[0025] Figure 2 A schematic diagram of the composition of a new energy optimal installed capacity prediction system provided in Example 2 of the present invention. DETAILED DESCRIPTION
[0026] Example:
[0027] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.
[0028] See also Figure 1 As shown, the new energy optimal installed capacity prediction method provided in this embodiment mainly includes the following steps:
[0029] Input the parameters of the power system in a certain area to be predicted and give the initial values of the decision variables at the power system level, pass them to the security constraint economic dispatch model for solution, and calculate the node electricity price at each time under the current new energy installed capacity penetration rate. Specifically, the values of the power system parameters include the power system grid structure, line parameters, unit data, new energy forecast output, and load data for each time period;
[0030] The node electricity price at each moment under the current penetration rate of new energy installed capacity is calculated as the input of the risk assessment index model. The risk index values of the three parties, namely the new energy developer side, the user side and the power grid side, are calculated through the risk assessment index model.
[0031] In this step, the risk index values of the three parties, namely, the renewable energy developer side (referred to as source), the user side (referred to as load), and the power grid side (referred to as network), are calculated through the risk assessment index model. The risks and interests of the three parties, namely, "source, network, and load" in the power system are comprehensively considered, and a scientific and reasonable risk assessment of the penetration rate of different renewable energy installed capacities is achieved, so as to ensure the safe and balanced operation of the power system.
[0032] Using the risk index value as an input of a comprehensive risk assessment index calculation model to obtain a comprehensive risk assessment index value under the current permeability;
[0033] The installed capacity of new energy is changed according to the set penetration rate increment Dk, and the installed capacity of conventional units is changed proportionally. The calculation is brought into the safety constrained economic dispatch model. If the upper limit kmax set for the penetration rate of new energy installed capacity is reached, the calculation is completed, and the comprehensive risk assessment index value corresponding to each penetration rate k is output to generate a comprehensive risk assessment index curve with the independent variable being the new energy installed capacity penetration rate k and the dependent variable being the comprehensive risk assessment index. Among them, the installed capacity penetration rate corresponding to the lowest point of the comprehensive risk assessment index curve is the optimal installed capacity penetration rate of new energy, corresponding to the optimal installed capacity of new energy.
[0034] In this way, the method of the present invention adopts the optimization idea and proposes a new energy optimal installed capacity prediction method based on the new energy installed capacity penetration rate risk assessment index model, which realizes the optimal prediction of new energy installed capacity. In the power market environment, it can help power companies and users improve market risk identification and assessment, provide decision-making references for installed capacity for new energy manufacturers, and help new energy manufacturers to reasonably allocate relevant resources and production capacity. Compared with the traditional installed capacity prediction, the prediction method of the present invention can comprehensively consider the risks and interests of the source, the network, and the load, and predict the new energy installed capacity that is win-win and balanced for the three parties from the optimal perspective, realizing a scientific and reasonable risk assessment of different new energy installed capacity penetration rates, so as to ensure the safe and balanced operation of the power system.
[0035] In a specific embodiment, the objective function of the safety-constrained economic dispatch model used in the present invention is:
[0036]
[0037] Among them, C i,t represents the operating cost of unit i at time t, P i,trepresents the output of unit i at time t, M1 represents the network power flow constraint relaxation penalty factor used for market clearing optimization; They represent the forward and reverse power flow relaxation variables of line l respectively; NL is the total number of lines; They represent the positive and negative flow relaxation variables of section s respectively; NS is the total number of sections; M2 is the power penalty factor for abandoned water in the hydropower plant; is the abandoned power of hydropower plant i at time t, M3 is the abandoned power penalty factor of the new energy trading unit, is the abandoned power of the new energy trading unit r in time period t.
[0038] Power balance constraints:
[0039]
[0040] Spinning reserve constraints:
[0041]
[0042] Unit output constraints:
[0043] P Gi,min ≤P Gi (t)≤P Gi,max (4)
[0044] New energy output constraints:
[0045] 0#P Windi (t) P Windi,f (t )(5)
[0046] 0#P PVi (t) P PVi,f (t) (6)
[0047] Unit climbing constraints:
[0048]
[0049] Active power flow constraints of the line:
[0050]
[0051] Active power flow constraints of the section:
[0052]
[0053] Among them, P Gi (t) represents the active output of conventional unit i at time t; P PVi,t represents the active output of photovoltaic unit i at time t; P Windi,t represents the active power output of wind power unit i at time t; P Load,trepresents the total load of the load system at time t; P Gi,max represents the upper limit of active output of conventional unit i at time t, P Gi,min represents the lower limit of active power output of conventional unit i at time t, represents the upper limit of active power output of conventional unit i at time t, P Windi,f (t) represents the predicted output of wind power unit i at time t, P PVi,f (t) represents the predicted output of photovoltaic unit i at time t, r ui represents the maximum ramp rate of conventional unit i, r di represents the maximum down-slope rate of conventional unit i, represents the upper limit of the active power of the transmission line from node m to node n, Pl mn (t) represents the active power of the transmission line from node m to node n, represents the power flow transmission limit of section s, and Ps(t) represents the active power of section s at time t.
[0054] Node electricity price calculation model:
[0055]
[0056] Among them, LMP i,t represents the node electricity price of node i at time t, λ t represents the Lagrange multiplier for the load balancing constraint, The Lagrange multiplier of the maximum forward power flow constraint of line l. When the line power flow exceeds the limit, the Lagrange multiplier is the penalty factor for the relaxation of the network power flow constraint. The Lagrangian multiplier of the maximum reverse power flow constraint on line l. When the line power flow exceeds the limit, the Lagrangian multiplier is the penalty factor for relaxing the network power flow constraint. is the Lagrangian multiplier of the maximum positive flow constraint of section s. When the section flow exceeds the limit, the Lagrangian multiplier is the penalty factor for the relaxation of the network flow constraint. is the Lagrangian multiplier of the maximum positive flow constraint of section s. When the section flow exceeds the limit, the Lagrangian multiplier is the penalty factor for the relaxation of the network flow constraint. is the Lagrange multiplier of the maximum reverse power flow constraint of section s. When the power flow of section s exceeds the limit, the Lagrange multiplier is the penalty factor for the relaxation of the network power flow constraint. G l-k G represents the generator output power transfer distribution factor of node i to line k; s-k Generator output power transfer distribution factor for node k to section s
[0057] In a specific embodiment, the risk assessment index model is used to calculate the market risk equilibrium point of the three parties of the new energy power generation company side, the user side, and the power grid side, so as to achieve a win-win situation for all three parties. The new energy power generation company side includes three risk indicators, namely, the volatility of the new energy power generation company's income grate 、The volatility of electricity price for new energy power generators k , New energy power generation company abandonment rate C rate,g .
[0058] Specifically, the volatility of the revenue of new energy power generators is g rate Refers to: the rate of change of the revenue of new energy power generators as the penetration rate of new energy installed capacity k changes, that is, the ratio of the revenue of renewable energy power generators corresponding to the current installed capacity penetration rate k to the revenue of new energy power generators corresponding to the next installed capacity penetration rate k+Δk; S k,i It is expressed as the revenue of renewable energy power producer i under installed capacity penetration rate; N is the number of renewable energy power producers, T is the calculation time period, Δk is the change in installed capacity penetration rate, which is 0.01 and can be set and changed.
[0059]
[0060]
[0061] The volatility rate of the electricity price traded by the new energy power company cv k Indicates the volatility of the electricity price curve of new energy power generators in the spot market; calculates the volatility of the electricity price curve of new energy power generators, expressed by the data dispersion index, and uses the coefficient of variation to represent the dispersion of the electricity price, where σ is the standard deviation of the curve and μ is the mean of the curve:
[0062]
[0063]
[0064]
[0065]
[0066] The power abandonment rate of the new energy power company is C rate,g Refers to: the ratio of the amount of electricity abandoned by new energy power generators to the predicted output of new energy power generators:
[0067]
[0068] The user side includes 1 risk indicator, which is the user electricity fee volatility y rate , with the change of installed capacity k, the change rate of the user's total electricity fee is the ratio of the total electricity fee of the user corresponding to the current new energy installed capacity penetration rate k to the total electricity fee of the user corresponding to the next installed capacity penetration rate k+Δk. k,i It is expressed as the total cost of users on node i under installed capacity penetration k, N is the number of nodes, P Lk,t is the total active load of users at node k at time t and M is the number of users.
[0069]
[0070]
[0071] The grid side includes two risk indicators: the grid side return volatility d rate and the grid-side node electricity price limit rate C limit ; The grid-side revenue volatility d rate , is the grid-side revenue corresponding to the current new energy installed capacity penetration rate k, that is, the total electricity fee of users minus the total revenue of new energy generators, and the ratio of the grid-side revenue corresponding to the next installed capacity penetration rate k+Δk:
[0072]
[0073] The power price limit rate C of the node on the grid side limit It refers to the proportion of nodes whose electricity prices are connected to the maximum price limit to the total number of nodes, reflecting the risk of power generation companies’ alliances driving up prices and manipulating the market.
[0074]
[0075] Among them, N LMPmax is the number of nodes whose electricity price reaches the limit, and N is the total number of nodes.
[0076] Since the measurement units of various indicators are not uniform, they need to be standardized before they are used to calculate the comprehensive index, that is, the absolute value of the indicator is converted into a relative value, so as to solve the homogeneity problem of the values of various different indicators. In this embodiment, the comprehensive risk assessment index calculation model adopts the range change method, as shown in the following formula:
[0077]
[0078] Among them, X k,i represents the i-th risk indicator corresponding to the penetration rate of new energy installed capacity k, where i is 1, 2, 3, 4, 5, 6; minX i Indicates the minimum value of the i-th indicator, maxX i represents the maximum value of the i-th index,
[0079] Z k It represents the comprehensive risk assessment index corresponding to the penetration rate of new energy installed capacity k. The calculation formula is as follows:
[0080]
[0081] In summary, compared with the prior art, the present invention has the following technical advantages:
[0082] (1) A risk assessment model for the penetration rate of renewable energy installed capacity is proposed, which comprehensively considers the risks and interests of the three parties of "source, grid and load" in the power system, and realizes a scientific and reasonable risk assessment of the penetration rate of different renewable energy installed capacity, so as to ensure the safe and balanced operation of the power system, and fills the gap in the risk assessment model in the field of renewable energy installed capacity prediction.
[0083] (2) A method for calculating the optimal installed capacity of new energy based on a risk assessment model for the penetration rate of new energy installed capacity is proposed. This method predicts the installed capacity of new energy from an optimal perspective, taking into account the interests of the three parties in the power system, namely, the source, the grid, and the load, and effectively reducing the decision-making risks of all parties involved in the development of new energy such as wind and solar power.
[0084] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.
[0085] Embodiment 2:
[0086] See also Figure 2 As shown, the new energy optimal installed capacity prediction system provided in this embodiment includes a processor 21, a memory 22, and a computer program 23 stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program 23, the steps of the above-mentioned embodiment 1 are implemented, for example Figure 1 Steps shown.
[0087] Exemplarily, the computer program 23 may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 23 in the new energy optimal installed capacity prediction system.
[0088] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0089] The memory 22 may be an internal storage unit of the optimal installed capacity prediction system for new energy, such as a hard disk or memory of the optimal installed capacity prediction system for new energy. The memory 22 may also be an external storage device of the optimal installed capacity prediction system for new energy, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the optimal installed capacity prediction system for new energy. Furthermore, the memory 22 may also include both an internal storage unit and an external storage device of the optimal installed capacity prediction system for new energy. The memory 22 is used to store the computer program and other programs and data required by the optimal installed capacity prediction system for new energy. The memory 22 may also be used to temporarily store data that has been output or is to be output.
[0090] Embodiment 3:
[0091] This embodiment provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.
[0092] The computer-readable medium shown can be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or apparatus or in conjunction with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable media on which the program can be printed, such as by optically scanning the paper or other medium, then editing, interpreting or processing in other suitable ways as necessary to obtain the program electronically, and then storing it in a computer memory.
[0093] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable ordinary technicians in the field to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made based on the essence of the content of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for predicting the optimal installed capacity of new energy. It is characterized in that The method comprises: Input the parameters of the regional power system to be predicted and give the initial values of the power system-level decision variables, pass them to the security-constrained economic dispatch model for solution, and calculate the node electricity price at each time under the current new energy installed capacity penetration rate; The node electricity price at each moment under the current penetration rate of new energy installed capacity is calculated as the input of the risk assessment index model, and the risk index values of the three parties, namely, the new energy developer side, the user side and the power grid side, are calculated through the risk assessment index model; Using the risk index value as an input of a comprehensive risk assessment index calculation model to obtain a comprehensive risk assessment index value under the current permeability; The installed capacity of new energy is changed according to the set penetration rate increment, and the installed capacity of conventional units is changed proportionally. The calculation is brought into the safety constrained economic dispatch model. If the upper limit kmax set for the installed capacity penetration rate of new energy is reached, the calculation is completed, and the comprehensive risk assessment index value corresponding to each penetration rate k is output to generate a comprehensive risk assessment index curve with the independent variable being the installed capacity penetration rate k of new energy and the dependent variable being the comprehensive risk assessment index. Among them, the installed capacity penetration rate corresponding to the lowest point of the comprehensive risk assessment index curve is the optimal installed capacity penetration rate of new energy, corresponding to the optimal installed capacity of new energy.
2. The method for predicting the optimal installed capacity of new energy according to claim 1, It is characterized in that The objective function of the safety-constrained economic dispatch model is: Among them, C i,t represents the operating cost of unit i at time t, P i,t represents the output of unit i at time t, M 1 represents the network power flow constraint relaxation penalty factor for market clearing optimization; They represent the forward and reverse power flow relaxation variables of line l respectively; NL is the total number of lines; They represent the positive and negative flow relaxation variables of section s respectively; NS is the total number of sections; M 2 is the power penalty factor for abandoned water in hydropower plants; is the abandoned water power of hydropower plant i at time t, M 3 is the penalty factor for power abandonment of new energy trading units, is the abandoned power of the new energy trading unit r in time period t.
3. The method for predicting the optimal installed capacity of new energy as claimed in claim 2, It is characterized in that The constraints of the safety-constrained economic dispatch model include: Power balance constraints: Spinning reserve constraints: Unit output constraints: P Gi,min ≤P Gi (t)≤P Gi,max (4) New energy output constraints: 0#P Windi (t) P Windi,f (t) (5) 0#P PVi (t) P PVi,f (t) (6) Unit climbing constraints: Active power flow constraints of the line: Active power flow constraints of the section: Among them, P Gi (t) represents the active output of conventional unit i at time t; P PVi,t represents the active output of photovoltaic unit i at time t; P Windi,t represents the active power output of wind power unit i at time t; P Load,t represents the total load of the load system at time t; P Gi,max represents the upper limit of active output of conventional unit i at time t, P Gi,min represents the lower limit of active power output of conventional unit i at time t, represents the upper limit of active power output of conventional unit i at time t, P Windi,f (t) represents the predicted output of wind power unit i at time t, P PVi,f (t) represents the predicted output of photovoltaic unit i at time t, r ui represents the maximum ramp rate of conventional unit i, r di represents the maximum down-slope rate of conventional unit i, represents the upper limit of the active power of the transmission line from node m to node n, Pl mn (t) represents the active power of the transmission line from node m to node n, represents the power flow transmission limit of section s, and Ps(t) represents the active power of section s at time t.
4. The method for predicting the optimal installed capacity of new energy according to claim 1, It is characterized in that The risk assessment index model is used to calculate the market risk equilibrium point of the three-party equilibrium of the new energy power generator side, the user side and the power grid side.
5. The method for predicting the optimal installed capacity of new energy as claimed in claim 4, It is characterized in that The new energy power generation company side includes three risk indicators, namely, the volatility of the new energy power generation company's income g rate 、The volatility of electricity price for new energy power generators k , New energy power generation company abandonment rate C rate,g ; The volatility of the new energy power generator's income g rate Refers to: the rate of change of the revenue of new energy power generators as the penetration rate of new energy installed capacity k changes, that is, the ratio of the revenue of renewable energy power generators corresponding to the current installed capacity penetration rate k to the revenue of new energy power generators corresponding to the next installed capacity penetration rate k+Δk; S k,i It is expressed as the revenue of new energy power producer i under the installed capacity penetration rate; N is the number of new energy power producers, T is the calculation time period, and Δk is the change in installed capacity penetration rate: The volatility rate of the electricity price of new energy power generators is cv k Indicates the volatility of the electricity price curve of new energy power generators in the spot market; calculates the volatility of the electricity price curve of new energy power generators, expressed by the data dispersion index, and uses the coefficient of variation to represent the dispersion of the electricity price, where σ is the standard deviation of the curve and μ is the mean of the curve: The power abandonment rate C of new energy power generators rate,g Refers to: the ratio of the amount of electricity abandoned by new energy power generators to the predicted output of new energy power generators:
6. The method for predicting the optimal installed capacity of new energy according to claim 4, It is characterized in that The user side includes one risk indicator, which is the user electricity fee volatility y rate :
7. The method for predicting the optimal installed capacity of new energy according to claim 4, It is characterized in that The grid side includes two risk indicators: the grid side return volatility d rate and the grid-side node electricity price limit rate C limit ; The grid-side revenue volatility d rate It is the ratio of the grid-side revenue corresponding to the current new energy installed capacity penetration rate k to the grid-side revenue corresponding to the next installed capacity penetration rate k+Δk: The grid-side node electricity price limit rate C limit Refers to the ratio of the number of nodes whose electricity prices are connected to the maximum price limit to the total number of nodes: Among them, N LMPmax is the number of nodes whose electricity price reaches the limit, and N is the total number of nodes.
8. The method for predicting the optimal installed capacity of new energy according to claim 1, It is characterized in that The comprehensive risk assessment index calculation model adopts the range change method, as shown in the following formula: Among them, X k,i represents the i-th risk indicator corresponding to the penetration rate of new energy installed capacity k, where i is 1, 2, 3, 4, 5, 6; min X i represents the minimum value of the i-th indicator, max X i represents the maximum value of the i-th index, Z k It represents the comprehensive risk assessment index corresponding to the penetration rate of new energy installed capacity k. The calculation formula is as follows:
9. A new energy optimal installed capacity prediction system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.
10. A computer-readable storage medium storing a computer program. It is 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 8 are implemented.
