A photovoltaic-photothermal ground base combined operation optimization method under spot market mode

Abstract

This invention relates to the fields of power system operation and electricity market technology, and particularly to a method, apparatus, equipment, and computer-readable storage medium for optimizing the joint operation of photovoltaic (PV) and solar thermal power (CSP) bases under a spot market model. The method includes: constructing a CSP unit production model; constructing a PV / CSP joint base production and operation simulation model based on the CSP unit production model; acquiring meteorological data and market boundary data to establish a spot market price prediction model; constructing a bidding strategy optimization model for the PV / CSP base participating in the spot market based on the PV / CSP joint base production and operation simulation model and the spot market price prediction model; and solving the bidding strategy optimization model using a preset optimization algorithm to generate the optimal joint operation of the PV / CSP base. By establishing a joint production model, XGBoost electricity price prediction, and profit maximization optimization model, the operational economy, strategy accuracy, and decision-making feasibility of the joint base in the spot market are improved.

Description

Technical Field

[0001] This application relates to the fields of power system operation and power market technology, and in particular to a method, apparatus, electronic equipment and computer-readable storage medium for the joint operation optimization of photovoltaic and solar thermal power bases under a spot market model. Background Technology

[0002] With the rapid transformation of my country towards clean and low-carbon energy, new energy power generation, primarily wind and solar power, is developing rapidly. Meanwhile, concentrated solar power (CSP) plants, through thermal storage devices, can achieve indirect time-series decoupling of solar energy and electricity, enabling them to transfer heat generation during peak load and power transmission periods, as well as during periods of high spot market prices. This provides them with good regulation capabilities and market economic benefits, making them an important peak-shaving resource for future power systems. As CSP installed capacity continues to increase, leveraging the energy time-shifting characteristics of thermal storage systems, CSP power generators have gained the ability to influence market-clearing prices, thereby enabling energy arbitrage across time and space. Therefore, it is necessary to establish a scientific and effective spot market strategy bidding model for CSP plants to improve their market returns.

[0003] Existing research primarily focuses on market players such as traditional fossil fuels, energy storage, and virtual power plants, with few studies deeply analyzing the bidding strategies and economic impacts of concentrated solar power (CSP) plants with thermal storage systems participating in the electricity spot market. Based on the capacity and market position of CSP plants, bidding strategies are typically categorized into price-taking strategies and bidding strategies. Furthermore, in addressing market clearing uncertainty, existing research generally employs scenario-based stochastic optimization methods or robust optimization to handle uncertainty issues. However, scenario-based stochastic optimization methods face significant challenges in solving high-dimensional mixed-integer linear programming problems across multiple scenarios due to the sheer number of scenarios and the massive computational demands; while robust optimization, while ensuring robustness, often suffers from overly conservative results and high economic costs.

[0004] In summary, current research on the participation of concentrated solar power (CSP) plants in the electricity market still has the following significant shortcomings: The lack of operational scenarios for the combined participation of photovoltaic (PV) and CSP units in the market makes the modeling, calculation, and solution of peak-shaving capacity and time-of-use regulation characteristics in such scenarios extremely complex; the peak-shaving needs of different CSP combined energy base systems vary significantly; CSP plant capacity planning primarily focuses on economic efficiency, supplemented by production and operation simulation constraints. However, how to comprehensively consider the thermal storage duration and plant capacity of CSP plants to improve the market competitiveness and economic efficiency of the base system under different wind and solar resource endowments and capacity ratios is an urgent problem to be solved. Summary of the Invention

[0005] This application aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the first objective of this application is to propose an optimization method for the joint operation of photovoltaic and solar thermal bases under the spot market model, in order to solve the problems of lack of modeling and complexity of solution for joint operation scenarios, inaccurate peak-shaving capacity and benefit assessment, and disconnect between planning and operation objectives in existing technologies.

[0007] The second objective of this application is to provide an apparatus.

[0008] The third objective of this application is to propose an electronic device.

[0009] The fourth objective of this application is to provide a computer-readable storage medium.

[0010] To achieve the above objectives, the first aspect of this application proposes an optimization method for the joint operation of photovoltaic and solar thermal power bases under a spot market model, comprising:

[0011] Based on the coupling characteristics of the solar thermal power generation system, the solar thermal power unit production model is constructed. Based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal unit, a production and operation simulation model of the photovoltaic-solar thermal integrated base is constructed. Acquire meteorological and market boundary data, and establish a spot market price forecasting model through correlation analysis; With the goal of maximizing profits in the spot market, an optimization model for the bidding strategy of the photovoltaic and solar thermal base in the spot market is constructed based on the production and operation simulation model of the photovoltaic and solar thermal base and the spot market price prediction model. The bidding strategy optimization model is solved using a preset optimization algorithm to generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

[0012] Preferably, the construction of the solar thermal power unit production model based on the coupling characteristics of the solar collection system, thermal storage system, and power generation system includes: Based on the photothermal conversion efficiency of the solar thermal power plant's solar thermal collection and absorption system and the solar radiation intensity, determine the heat absorbed by the solar collection system and the heat stored in the thermal storage system. The operational constraints of the thermal storage system are constructed, including at least: thermoelectric conversion constraints, electrothermal conversion constraints with electric heating devices, thermal balance constraints of the thermal storage system, and upper and lower limits of the thermal storage system capacity. Construct operational simulation constraints for solar thermal power plant units, which include at least: unit start-up and shutdown time constraints, upper and lower limits of power output constraints, ramp-up capability constraints, and annual utilization hours constraints.

[0013] Preferably, the construction of a production and operation simulation model for the photovoltaic-thermal integrated base based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal unit includes: The power balance constraint of the photovoltaic and solar thermal integrated base is to ensure that the sum of the photovoltaic power generation output and the solar thermal power generation output equals the power output of the base. Construct photovoltaic output constraints and determine the theoretical photovoltaic output based on the installed capacity of photovoltaic power plants and normalized power generation. Establish a power transmission limit constraint for the base to ensure that the power transmitted from the base does not exceed a preset transmission limit; To establish constraints on renewable energy curtailment, the total amount of curtailment and the curtailment rate of the base are determined based on the theoretical power generation capacity of photovoltaics, the actual curtailed power of photovoltaics, and a given deviation threshold.

[0014] Preferably, the acquisition of meteorological data and market boundary data, and the establishment of a spot market price forecasting model through correlation analysis, includes: Calculate the correlation coefficients between meteorological forecast data and market boundary data and day-ahead spot prices and real-time spot prices, and screen characteristic variables; the meteorological forecast data includes at least temperature, humidity, cloud cover, sunshine duration and wind speed; Based on the selected feature variables, a spot clearing electricity price prediction model is trained using the XGBoost algorithm. The XGBoost algorithm constructs multiple decision trees, uses the residual of the previous decision tree to fit the next decision tree, and sums the fitted values ​​of all decision trees to obtain the final electricity price prediction value.

[0015] Preferably, the objective function configuration of the optimization model for the photovoltaic and solar thermal base's participation in the spot market bidding strategy includes: The objective is to maximize the total market profit of photovoltaic and solar thermal power units. The total market profit includes the medium- and long-term market profit of electricity and the spot market profit. The medium- and long-term market profit of electricity is determined based on the winning bid electricity and winning bid price in the medium- and long-term trading market and the average price at the current day spot market node. The spot market profit is determined based on the current day spot clearing volume, the real-time spot clearing volume, the current day spot clearing price forecast, and the real-time spot clearing price forecast.

[0016] Preferably, the bidding strategy optimization model further includes: solar thermal power unit price constraints, which include: constructing a piecewise function for solar thermal power unit price, such that the bid price increases monotonically with each segment; setting the upper and lower limits of the unit output for segmented bids, as well as the minimum interval for segmented bid output and the minimum increment interval for spot segmented bids.

[0017] Preferably, solving the bidding strategy optimization model using a preset optimization algorithm includes: The differential evolution algorithm is used to solve the problem. The parent individuals are subjected to a mutation operation by superimposing a difference vector, and mutated individuals are generated, where the difference scaling factor controls the mutation amplitude. The crossover operator is used to cross over parent individuals and mutant individuals to generate experimental individuals; The selection operator compares the fitness values ​​of the parent individuals and the trial individuals, selects the individuals with better fitness values ​​to enter the next generation of the population, and continues until the iteration stops. The optimal solution is then output as the bidding strategy.

[0018] To achieve the above objectives, a second aspect of this application proposes a photovoltaic and solar thermal base joint operation optimization device under a spot market model, comprising: The unit modeling module constructs a production model for solar thermal power units based on the coupling characteristics of the solar collection system, thermal storage system, and power generation system. The base simulation module constructs a production and operation simulation model for the photovoltaic and solar thermal power plant based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal power unit. The price forecasting module acquires meteorological and market boundary data and establishes a spot market price forecasting model through correlation analysis. The strategy optimization module aims to maximize profits in the spot market. Based on the production and operation simulation model of the photovoltaic and solar thermal integrated base and the spot market price prediction model, it constructs an optimization model for the bidding strategy of the photovoltaic and solar thermal integrated base in the spot market. The strategy generation module uses a preset optimization algorithm to solve the bidding strategy optimization model and generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

[0019] To achieve the above objectives, a third aspect of this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method described in any of the preceding descriptions.

[0020] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium, comprising computer-executable instructions stored therein, which, when executed by a processor, are used to implement the method described in any of the above embodiments.

[0021] This application provides an optimization method for the joint operation of photovoltaic and solar thermal power bases under a spot market model. By establishing a production model for solar thermal power units and a simulation model for the joint operation of photovoltaic and solar thermal power bases, it systematically characterizes the coupling characteristics of solar thermal collection, heat storage, and power generation, as well as the joint operation constraints with photovoltaic output. This solves the problems of modeling and solving complex joint operation scenarios, improving the accuracy and practicality of optimization decisions. By constructing a spot market price prediction model and a bidding strategy optimization model with the goal of maximizing total revenue, it can accurately predict electricity price trends and dynamically optimize the timing of solar thermal storage / heat release and power generation output. It objectively evaluates the time-shifting capability of the solar thermal storage system and accurately calculates the arbitrage benefits brought by generating electricity during high-price periods and avoiding low-price periods. This achieves a precise quantitative assessment of the peak-shaving capability and market returns of solar thermal power plants, improving economic efficiency. The application uses a data-driven XGBOOST model for electricity price prediction, effectively utilizing the complex nonlinear relationships in historical meteorological and market data, overcoming the shortcomings of traditional optimization methods in handling uncertainty, and achieving a good balance between economic efficiency and robustness.

[0022] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0023] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of a first specific embodiment of an optimization method for the joint operation of photovoltaic and solar thermal bases under a spot market model provided by the present invention; Figure 2 A flowchart of a second specific embodiment of the optimization method for joint operation of photovoltaic and solar thermal bases under a spot market model provided by the present invention; Figure 3 This is a structural block diagram of a photovoltaic and solar thermal base joint operation optimization device under a spot market model, provided as an embodiment of the present invention. Detailed Implementation

[0024] The core of this invention is to provide a method, apparatus, electronic device, and computer-readable storage medium for the joint operation optimization of photovoltaic and solar thermal bases under a spot market model. By establishing a joint production model, XGBoost electricity price prediction, and profit maximization optimization model, the invention improves the operational economy, strategy accuracy, and decision-making feasibility of joint bases in the spot market.

[0025] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Please refer to Figure 1 , Figure 1 The flowchart illustrates a first specific embodiment of the optimized joint operation method for photovoltaic and solar thermal power bases under a spot market model provided by the present invention; the specific operation steps are as follows: Step S101: Based on the coupling characteristics of the solar thermal power generation system, the thermal storage system, and the power generation system, construct a production model for the solar thermal power unit; Step S102: Based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal unit, construct a production and operation simulation model for the photovoltaic-solar thermal integrated base; Step S103: Obtain meteorological data and market boundary data, and establish a spot market price forecasting model through correlation analysis; Step S104: With the goal of maximizing spot market profits, based on the production and operation simulation model of the photovoltaic and solar thermal integrated base and the spot market price prediction model, construct an optimization model for the bidding strategy of the photovoltaic and solar thermal base participating in the spot market; Step S105: Solve the bidding strategy optimization model using a preset optimization algorithm to generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

[0027] Based on the above embodiments, this embodiment will provide a detailed description of step S101: In one embodiment, the heat absorbed by the solar thermal power plant and the heat stored in the thermal storage system are determined based on the photothermal conversion efficiency of the solar thermal power plant's solar thermal collection and absorption system and the solar radiation intensity. The operational constraints of the thermal storage system are constructed, including at least: thermoelectric conversion constraints, electrothermal conversion constraints with electric heating devices, thermal balance constraints of the thermal storage system, and upper and lower limits of the thermal storage system capacity. Construct operational simulation constraints for solar thermal power plant units, which include at least: unit start-up and shutdown time constraints, upper and lower limits of power output constraints, ramp-up capability constraints, and annual utilization hours constraints.

[0028] Specifically, the operation simulation of the solar collection and thermal storage system: The solar collection system is primarily responsible for reflecting solar irradiance energy to the heat absorption device and transferring the heat energy to the thermal storage system. However, due to the influence of the site and the operating efficiency of the solar collection system, the system's conversion efficiency exhibits nonlinear characteristics under different irradiance levels. Therefore, a linearized photothermal conversion efficiency is used for modeling: The heat absorbed by the solar collection system is:

[0029] in, For a moment Solar radiation intensity at the new energy base; The photothermal conversion efficiency of the solar thermal power plant's solar thermal absorption system.

[0030] The amount of heat stored in the solar energy storage system that flows into the solar energy storage system can also be expressed as:

[0031] in, The rated power generation capacity of the solar thermal power plant unit; To disregard the overall photothermal conversion efficiency dissipated by the energy storage system; For solar thermal power units The solar multiplier of a solar concentrator system characterizes the ratio of the heat energy absorbed by the solar concentrator system to the heat energy absorbed by the equivalent heat energy when converted into the rated power output of a solar thermal power plant. It is generally taken as 1.5-3.0.

[0032] The thermal storage system includes the thermoelectric conversion constraints of the thermal storage system for generating electricity through heat release, the electrothermal conversion constraints of the system equipped with electric heating devices, the thermal balance constraints of the thermal storage system, and the upper and lower limits of the thermal storage system capacity.

[0033] The thermoelectric conversion constraint formula is:

[0034] In the formula: This refers to the serial number of the solar thermal power unit; For the unit exist Power generation at any given moment; For the unit exist The heat power consumed by the power generation at any given moment; This represents the thermoelectric conversion relationship function. Typically, this conversion relationship is a nonlinear constraint due to the influence of conversion efficiency under different power outputs. In this embodiment, for ease of solution during the planning phase, this constraint is defined as a linear constraint.

[0035] The electrothermal conversion constraint formula for an electric heating device is:

[0036] In the formula: This refers to the serial number of the electric heating device in the solar thermal power unit; Electric heating device exist The electrical power consumed during a given period; This corresponds to the generated heat power; This indicates the electrothermal conversion relationship.

[0037] The formulas for satisfying the thermal balance constraint and the thermoelectric conversion constraint during solar thermal power generation for the thermal storage system are as follows:

[0038] In the formula: Indicates solar thermal power unit thermal storage system in The thermal energy of the thermal storage system is constantly being stored. , These respectively represent the thermal storage system in The heat storage and release power at any given time; The dissipation coefficient; , These refer to the heat storage and heat release efficiencies of the thermal storage system, respectively. Photothermal-thermal-electric conversion efficiency; This is the solar energy multiplier, typically ranging from 1.5 to 3.0.

[0039] The thermal storage system must meet the following capacity upper and lower limit constraints:

[0040]

[0041]

[0042] In the formula: , The units The upper and lower limits of the capacity of the thermal storage system; The thermal storage duration of the thermal storage system characterizes the duration during which the thermal storage system can generate electricity at the rated power output of the solar thermal power unit. Generally, 4 to 15 hours are taken. This represents the minimum percentage of thermal storage capacity.

[0043] Solar thermal power plant unit operation simulation The operation of a concentrated solar power (CSP) plant is similar to that of a thermal power unit because it uses a steam turbine generator for simulation. However, the operation of the unit is limited by thermoelectric conversion and upstream heat energy flow, and the unit model parameters also differ. The specific model is as follows: The start-up and shutdown constraint formula for solar thermal power units is:

[0044] In the formula: For solar thermal power units Minimum shutdown time, Solar thermal power units Minimum boot time; for Solar thermal power units during the period The running status.

[0045] The formulas for the upper and lower limits of output constraints are:

[0046] In the formula: , For solar thermal power units Maximum and minimum power generation during normal operation for The operating status of the solar thermal power plant during a certain period of time. At that time, the steam turbine generator set stopped. At that time, the steam turbine generator set was running.

[0047] The slope constraint formula is:

[0048] In the formula , They are solar thermal power units Maximum climbing ability.

[0049] The annual utilization hours constraints for solar thermal power plants are as follows:

[0050] In the formula For solar thermal power units Design annual utilization hours For solar thermal power units The rated installed capacity.

[0051] Based on the above embodiments, this embodiment will provide a detailed description of step S102: In one embodiment, a power balance constraint is constructed for the photovoltaic-thermal integrated base, such that the sum of the photovoltaic power generation output and the solar thermal power generation output equals the power transmitted from the base. Construct photovoltaic output constraints and determine the theoretical photovoltaic output based on the installed capacity of photovoltaic power plants and normalized power generation. Establish a power transmission limit constraint for the base to ensure that the power transmitted from the base does not exceed a preset transmission limit; To establish constraints on renewable energy curtailment, the total amount of curtailment and the curtailment rate of the base are determined based on the theoretical power generation capacity of photovoltaics, the actual curtailed power of photovoltaics, and a given deviation threshold.

[0052] Specifically, the constraints of the solar thermal energy storage + new energy base include power balance constraints, solar thermal unit operation constraints, photovoltaic output constraints, base power transmission limit constraints, and photovoltaic curtailment constraints. The solar thermal unit operation constraints have been described in the above embodiments; the remaining constraints are as follows: The power balance constraint formula is:

[0053] In the formula, To ensure the continuous power generation output of photovoltaics; Power was supplied to the base; It generates electricity for solar thermal power units.

[0054] The photovoltaic output constraint formula is:

[0055] In the formula, For photovoltaic power stations Time-period normalized power generation This refers to the installed capacity of photovoltaic power plants.

[0056] The limit constraint formula for base transmission is:

[0057] In the formula, It is the power transmission limit of the solar thermal energy storage + photovoltaic base.

[0058] The formula for constraining the curtailment of renewable energy is:

[0059]

[0060]

[0061] In the formula, , These are respectively the amount of photovoltaic power curtailment and the theoretical power generation capacity. , This refers to the total amount of curtailed electricity and curtailed power in the solar thermal energy storage and photovoltaic (PV) bases, assuming the difference in PV curtailment rates within the new energy bases is less than a given deviation. .

[0062] Based on the above embodiments, this embodiment will provide a detailed description of step S103: In one embodiment, the correlation coefficients between meteorological forecast data and market boundary data and day-ahead spot prices and real-time spot prices are calculated, and characteristic variables are screened; the meteorological forecast data includes at least temperature, humidity, cloud cover, sunshine duration, and wind speed. Based on the selected feature variables, a spot clearing electricity price prediction model is trained using the XGBoost algorithm. The XGBoost algorithm constructs multiple decision trees, uses the residual of the previous decision tree to fit the next decision tree, and sums the fitted values ​​of all decision trees to obtain the final electricity price prediction value.

[0063] Specifically, the formula for price spread correlation analysis is:

[0064]

[0065] In the formula, , They represent in Real-time weather forecasts including temperature, humidity, cloud cover, sunshine duration, wind speed, and market boundary data. The values ​​of a vector matrix and its mean, and They are respectively the corresponding The day-ahead spot price and average at any given time. and They are respectively the corresponding Real-time spot prices and averages at any given time; , This is the correlation coefficient between meteorological forecasts of temperature, humidity, cloud cover, sunshine duration, wind speed, etc., and market boundary data, and day-ahead and real-time spot prices. Its value ranges between -1 and +1. or This indicates that the two variables are positively correlated; if or This indicates that the two variables are negatively correlated. or The larger the absolute value, the stronger the correlation; if or This indicates that there is no linear relationship between the two. or An absolute value between 0.4 and 0.6 indicates a moderate correlation, between 0.6 and 0.8 indicates a strong correlation, and between 0.8 and 1 indicates a very strong correlation.

[0066] In the inter-provincial spot clearing electricity price prediction model based on the XGBoost algorithm, ranking the importance of each feature variable's impact on the model's output day-ahead or real-time spot clearing electricity price facilitates model structure selection, reduces irrelevant sample types, improves the efficiency of collecting necessary samples, and enhances the model's computational speed and prediction accuracy. Modeling the tree-based XGBoost algorithm involves determining the tree model structure and the output values ​​of its leaf nodes.

[0067] The basic formula for XGBoost algorithm prediction is:

[0068] in: This is a predicted value; For the first One sample input; Let it be an independent function in space; The number of decision trees; Let be the function space consisting of all decision trees.

[0069] The basic process includes the following three steps: First, the dataset is fitted based on the first decision tree, and the residual between the actual value and the predicted value is calculated; second, a second decision tree is introduced based on the residual to fit the residual; when the residual meets a preset value, the introduction of decision trees is stopped; finally, the fitted values ​​of each decision tree are accumulated to obtain the final fitting result of the XGboost algorithm, which is expressed as follows:

[0070]

[0071] in, Let be the objective function. For loss function, This is a regularization penalty function to prevent overfitting. and The datasets are respectively the first and second. The true and predicted values ​​of each sample output. For the first The output prediction value of the decision tree This represents the number of samples. The number of leaf nodes; The weight of the leaf node; and These are pre-defined hyperparameters used to control the number of leaf nodes and their scores, respectively.

[0072] Based on the above embodiments, this embodiment will provide a detailed description of step S104: In one embodiment, the objective function configuration of the optimization model for the bidding strategy of photovoltaic and solar thermal power bases participating in the spot market includes: maximizing the total market profit of photovoltaic and solar thermal power units; the total market profit includes the medium- and long-term market profit of electricity and the spot market profit; the medium- and long-term market profit of electricity is determined based on the winning bid electricity, winning bid price and day-ahead average price of the spot market nodes in the medium- and long-term trading market; the spot market profit is determined based on the day-ahead spot clearing electricity volume, the real-time spot clearing electricity volume, the day-ahead spot clearing price forecast and the real-time spot clearing price forecast.

[0073] Specifically, the objective function expression for the optimization model of the bidding strategy for photovoltaic and solar thermal bases participating in the spot market is:

[0074] in, For photovoltaic and solar thermal units Total market profit; , These are photovoltaic and solar thermal power units. Profits in the long-term and spot markets for electrical energy. Among them: Photovoltaic and solar thermal units Profits in the medium- to long-term electricity market for:

[0075] in, This represents the total number of scheduling periods, typically 24 or 96. , These are photovoltaic and solar thermal power units. During the period Winning bids for electricity and electricity prices in the medium- and long-term trading market For photovoltaic and solar thermal units During the period The average price at the current spot market node; Power generation unit Profits in the spot market for electricity for:

[0076] in, , , , These are the day-ahead and real-time spot clearing volumes for solar thermal electricity and solar photovoltaic electricity, respectively. , These are the day-ahead and real-time spot clearing electricity price forecasts, respectively.

[0077] Constraints of the segmented monotonically increasing price range for solar thermal power units and the output-based bidding strategy:

[0078]

[0079] In the formula, and The function corresponding to the segmented line segment for pricing of solar thermal power units. , These represent the declared price and corresponding output of solar thermal power unit i in segment m, respectively. The total number of sections declared for thermal power plants; , The upper and lower limits of unit output will be declared in stages for the spot market; The minimum interval for segmented pricing output; This represents the minimum increment interval for segmented spot price quotes; , These represent the lower and upper limits of the spot market price, respectively.

[0080] Based on the above embodiments, this embodiment will provide a detailed description of step S105: In one embodiment, the differential evolution algorithm is used to solve the problem; The parent individuals are subjected to a mutation operation by superimposing a difference vector, and mutated individuals are generated, where the difference scaling factor controls the mutation amplitude. The crossover operator is used to cross over parent individuals and mutant individuals to generate experimental individuals; The selection operator compares the fitness values ​​of the parent individuals and the trial individuals, selects the individuals with better fitness values ​​to enter the next generation of the population, and continues until the iteration stops. The optimal solution is then output as the bidding strategy.

[0081] The bidding strategy optimization model also includes: solar thermal power unit pricing constraints, which include: constructing a piecewise function for solar thermal power unit pricing, such that the bid price increases monotonically with each segment; setting the upper and lower limits of the unit output for segmented bidding, as well as the minimum interval for segmented bidding output and the minimum increment interval for spot segmented bidding.

[0082] Specifically, model optimization employs a differential algorithm. This involves mutating parent individuals by superimposing differential vectors onto them. Then, with a certain probability, the parent individuals are compared with the experimental individuals, and the superior individuals are introduced into the next generation. Let the population size be NP, and the dimension of the individual decision variables be n. The model includes three operators: differential mutation, crossover, and selection, with the following expressions: Differential mutation operator. For each individual in the g-th generation of the population. Three distinct parent individuals were randomly selected. , , (r1, r2, r3 ∈ [1, NP] and r1, r2, r3 ≠ i), perform differential mutation operation to generate mutated individuals. for:

[0083] in, It is the difference scaling factor, which controls the magnitude of the difference variation.

[0084] Crossover operator. For parent individuals and mutated individuals Crossover is performed to generate experimental individuals. for:

[0085] in: The numbers are uniformly random numbers between [0, 1]; CR∈[0, 1] is the crossover probability. It is a random integer between [1, n] to ensure that at least one of the experimental individuals comes from the mutant individual.

[0086] Selection operator. Compare the fitness values ​​of the parent individuals and the experimental individuals; the one with the better fitness value enters the next generation population.

[0087] The XGBOSST model was trained using historical data, and the model parameters (such as the number of trees, maximum depth, etc.) were adjusted to optimize the model's predictive performance. Based on the Python language, the grid search method was used to calculate the cross-validation performance of various meteorological and market boundary parameters on the new sample training set, and the parameters were adjusted and optimized accordingly.

[0088] This embodiment provides an optimization method for the joint operation of photovoltaic and solar thermal power bases under a spot market model. By establishing a production model for solar thermal power units and a simulation model for the joint operation of photovoltaic and solar thermal power bases, it systematically characterizes the coupling characteristics of solar thermal collection, heat storage, and power generation, as well as the joint operation constraints with photovoltaic output. This solves the problems of modeling and solving complex joint operation scenarios, improving the accuracy and practicality of optimization decisions. By constructing a spot market price prediction model and a bidding strategy optimization model with the goal of maximizing total revenue, it can accurately predict electricity price trends. Based on this, it dynamically optimizes the timing of solar thermal storage / heat release and power generation output, objectively evaluates the time-shifting capability of the solar thermal storage system, and accurately calculates the arbitrage benefits brought by generating electricity during high-price periods and avoiding low-price periods. This achieves a precise quantitative assessment of the peak-shaving capability and market returns of solar thermal power plants, improving economic efficiency. The data-driven XGBOOST model is used for electricity price prediction, effectively utilizing the complex nonlinear relationships in historical meteorological and market data, overcoming the shortcomings of traditional optimization methods in handling uncertainties, and achieving a good balance between economic efficiency and robustness.

[0089] Based on the above embodiments, this embodiment describes a method for optimizing the joint operation of photovoltaic and solar thermal power bases under a spot market model, such as... Figure 2 As shown, the details are as follows: Step 1: System Initialization and Parameter Input Based on the physical configuration parameters of the photovoltaic-solar thermal power plant, the system model is initialized. Specifically, this includes: the solar collector efficiency, thermal storage capacity and efficiency parameters, generator rated power, and ramp-up capability of the solar thermal power plant; and the installed capacity and power characteristic curves of the photovoltaic power plant. Simultaneously, current weather forecast data (including solar irradiance, ambient temperature, etc.) and relevant boundary conditions from the electricity spot market are input.

[0090] Step 2: Production Simulation of Solar Thermal Power Units and Construction of Joint Base Model: Based on the parameters input in the first step, a production and operation simulation model for the solar thermal power unit is established. This model fully couples the three subsystems of solar energy collection, thermal energy storage, and power generation, describing the dynamic process of energy conversion and storage. Building upon this, and combining it with the photovoltaic power generation model, a complete production and operation simulation model for the photovoltaic and solar thermal integrated base is constructed. This model covers power balance constraints, equipment operation constraints, power transmission capacity constraints, and renewable energy consumption constraints.

[0091] Step 3: Spot Market Price Forecasting By utilizing historical meteorological data, market operation data, and real-time input boundary information, a machine learning model based on the XGBoost algorithm is employed to predict the clearing price of the electricity spot market for a certain future time period (e.g., the next 24 hours). This prediction model can capture the complex nonlinear relationship between electricity prices and various influencing factors, and output predicted electricity price sequences for the day-ahead market and the real-time market.

[0092] Step 4: Establishing and solving the bidding strategy optimization model: A bidding strategy optimization model is established with the goal of maximizing the total revenue of the joint base in the spot market. The core of this model is to use the production operation simulation model constructed in the second step as a physical constraint, the predicted electricity price obtained in the third step as an economic input, and to consider the bidding rules of the concentrated solar power (CSP) plant in the market (such as segmented bidding, price monotonicity, etc.). A differential evolution algorithm is used to solve this high-dimensional nonlinear optimization problem, outputting the optimal bidding strategy, namely the CSP / storage / heat release plan, the power generation output curve, and the corresponding market price curve.

[0093] Step 5: Strategy Output and Execution The optimal bidding strategy obtained from the optimization solution is output as an executable instruction set, including: power generation plans for solar thermal units at various times, heat storage / release operation instructions for the thermal energy storage system, and the official price quote curve submitted to the power trading institution. The system can submit bids in the spot market based on this strategy and guide the actual operation of the joint base.

[0094] Step 6: Data Update and Model Iteration At the end of an operating cycle (e.g., one day), actual meteorological data, market clearing results, and base operation data are collected. These new data samples are incorporated into the historical database for periodic retraining and updating of the electricity price forecasting model, and key parameters in the optimized model are calibrated to enable the system to continuously learn and self-optimize, adapting to changes in market environment and resource conditions.

[0095] Please refer to Figure 3 , Figure 3 This invention provides a structural block diagram of a photovoltaic and solar thermal base joint operation optimization device under a spot market model; the specific device may include: The unit modeling module 100 constructs a production model for a solar thermal power unit based on the coupling characteristics of the solar collection system, thermal storage system, and power generation system. The base simulation module 200 constructs a production and operation simulation model for the photovoltaic and solar thermal power plant based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal power unit. The price forecasting module 300 acquires meteorological data and market boundary data, and establishes a spot market price forecasting model through correlation analysis. The strategy optimization module 400 aims to maximize profits in the spot market. Based on the production and operation simulation model of the photovoltaic and solar thermal integrated base and the spot market price prediction model, it constructs an optimization model for the bidding strategy of the photovoltaic and solar thermal base participating in the spot market. The strategy generation module 500 uses a preset optimization algorithm to solve the bidding strategy optimization model and generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

[0096] This embodiment of a photovoltaic and solar thermal power plant joint operation optimization device under a spot market model is used to implement the aforementioned photovoltaic and solar thermal power plant joint operation optimization method under a spot market model. Therefore, the specific implementation of the photovoltaic and solar thermal power plant joint operation optimization device under a spot market model can be found in the embodiment section of the photovoltaic and solar thermal power plant joint operation optimization method under a spot market model mentioned above. For example, the unit modeling module 100, the base simulation module 200, the price prediction module 300, the strategy optimization module 400, and the strategy generation module 500 are respectively used to implement steps S101, S102, S103, S104, and S105 in the aforementioned photovoltaic and solar thermal power plant joint operation optimization method under a spot market model. Therefore, its specific implementation can be referred to the description of the corresponding embodiments, and will not be repeated here.

[0097] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0098] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0099] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0100] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0101] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0102] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0103] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0104] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0105] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0107] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0108] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0109] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0110] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for optimizing the joint operation of photovoltaic and solar thermal power bases under a spot market model, characterized in that, include: Based on the coupling characteristics of the solar thermal power generation system, the solar thermal power unit production model is constructed. Based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal unit, a production and operation simulation model of the photovoltaic-solar thermal integrated base is constructed. Acquire meteorological and market boundary data, and establish a spot market price forecasting model through correlation analysis; With the goal of maximizing profits in the spot market, an optimization model for the bidding strategy of the photovoltaic and solar thermal base in the spot market is constructed based on the production and operation simulation model of the photovoltaic and solar thermal base and the spot market price prediction model. The bidding strategy optimization model is solved using a preset optimization algorithm to generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

2. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The production model for solar thermal power units, based on the coupling characteristics of the solar collection system, thermal storage system, and power generation system, includes: Based on the photothermal conversion efficiency of the solar thermal power plant's solar thermal collection and absorption system and the solar radiation intensity, determine the heat absorbed by the solar collection system and the heat stored in the thermal storage system. The operational constraints of the thermal storage system are constructed, including at least: thermoelectric conversion constraints, electrothermal conversion constraints with electric heating devices, thermal balance constraints of the thermal storage system, and upper and lower limits of the thermal storage system capacity. Construct operational simulation constraints for solar thermal power plant units, which include at least: unit start-up and shutdown time constraints, upper and lower limits of power output constraints, ramp-up capability constraints, and annual utilization hours constraints.

3. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The construction of the photovoltaic-solar thermal power plant production and operation simulation model based on the characteristics of photovoltaic power generation resources and the solar thermal power unit production model includes: The power balance constraint of the photovoltaic and solar thermal integrated base is to ensure that the sum of the photovoltaic power generation output and the solar thermal power generation output equals the power output of the base. Construct photovoltaic output constraints and determine the theoretical photovoltaic output based on the installed capacity of photovoltaic power plants and normalized power generation. Establish a power transmission limit constraint for the base to ensure that the power transmitted from the base does not exceed a preset transmission limit; To establish constraints on renewable energy curtailment, the total amount of curtailment and the curtailment rate of the base are determined based on the theoretical power generation capacity of photovoltaics, the actual curtailed power of photovoltaics, and a given deviation threshold.

4. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The acquisition of meteorological data and market boundary data, and the establishment of a spot market price forecasting model through correlation analysis, includes: Calculate the correlation coefficients between meteorological forecast data and market boundary data and day-ahead spot prices and real-time spot prices, and screen characteristic variables; the meteorological forecast data includes at least temperature, humidity, cloud cover, sunshine duration and wind speed; Based on the selected feature variables, a spot clearing electricity price prediction model is trained using the XGBoost algorithm. The XGBoost algorithm constructs multiple decision trees, uses the residual of the previous decision tree to fit the next decision tree, and sums the fitted values ​​of all decision trees to obtain the final electricity price prediction value.

5. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The objective function configuration of the optimization model for the bidding strategy of the photovoltaic and solar thermal base participating in the spot market includes: The objective is to maximize the total market profit of photovoltaic and solar thermal power units. The total market profit includes the medium- and long-term market profit of electricity and the spot market profit. The medium- and long-term market profit of electricity is determined based on the winning bid electricity and winning bid price in the medium- and long-term trading market and the average price at the current day spot market node. The spot market profit is determined based on the current day spot clearing volume, the real-time spot clearing volume, the current day spot clearing price forecast, and the real-time spot clearing price forecast.

6. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The bidding strategy optimization model also includes: solar thermal power unit pricing constraints, which include: constructing a piecewise function for solar thermal power unit pricing, such that the bid price increases monotonically with each segment; setting the upper and lower limits of the unit output for segmented bidding, as well as the minimum interval for segmented bidding output and the minimum increment interval for spot segmented bidding.

7. The method for optimizing the joint operation of photovoltaic and solar thermal power bases under the spot market model according to claim 1, characterized in that, The step of solving the bidding strategy optimization model using a preset optimization algorithm includes: The differential evolution algorithm is used to solve the problem. The parent individuals are subjected to a mutation operation by superimposing a difference vector, and mutated individuals are generated, where the difference scaling factor controls the mutation amplitude. The crossover operator is used to cross over parent individuals and mutant individuals to generate experimental individuals; The selection operator compares the fitness values ​​of the parent individuals and the trial individuals, selects the individuals with better fitness values ​​to enter the next generation of the population, and continues until the iteration stops. The optimal solution is then output as the bidding strategy.

8. A photovoltaic and solar thermal base joint operation optimization device under a spot market model, characterized in that, include: The unit modeling module constructs a production model for solar thermal power units based on the coupling characteristics of the solar collection system, thermal storage system, and power generation system. The base simulation module constructs a production and operation simulation model for the photovoltaic and solar thermal power plant based on the characteristics of photovoltaic power generation resources and the production model of the solar thermal power unit. The price forecasting module acquires meteorological and market boundary data and establishes a spot market price forecasting model through correlation analysis. The strategy optimization module aims to maximize profits in the spot market. Based on the production and operation simulation model of the photovoltaic and solar thermal integrated base and the spot market price prediction model, it constructs an optimization model for the bidding strategy of the photovoltaic and solar thermal integrated base in the spot market. The strategy generation module uses a preset optimization algorithm to solve the bidding strategy optimization model and generate the optimal joint operation and bidding strategy for the photovoltaic and solar thermal base.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images