Park new energy consumption capability assessment method and device based on power generation cost and prediction error, and storage medium

Abstract

The invention provides a power generation cost and prediction error-based park new energy consumption capability assessment method and apparatus, and a storage medium, and relates to the technical field of industrial park power system optimization scheduling. The method comprises the following steps: step 1, constructing power generation models of different power generation resources in a park according to wind power photovoltaic power generation capacity constraints, thermal power generating unit operation constraints and energy storage equipment operation constraints; 2, adjusting new energy consumption based on the load demand response potential of the park, and constructing an upper-layer consumption model by taking the maximum consumption amount as a target function; 3, according to the operation cost of the thermal power generating unit, the adjustment cost of the energy storage equipment and the adjustment cost of the load, constructing a lower-layer cost model by taking the minimum total cost as an objective function; and 4, evaluating the new energy consumption capability of the park based on the power generation model, the upper-layer consumption model and the lower-layer cost model. The utilization rate of renewable resources is improved, the resource cost is saved, and the accuracy of evaluating the new energy consumption capability is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial park power system optimization and dispatching, and in particular to a method, device and storage medium for evaluating the new energy consumption capacity of an industrial park based on power generation cost and prediction error. Background Art

[0002] Countries around the world are accelerating the transformation of their energy structures, focusing on the development of renewable energy such as wind power and photovoltaics. Against this background, my country has actively introduced policies to support the development and consumption of new energy, and emphasized optimizing energy allocation from both the supply and demand sides to promote the coordinated development of the economy, society and the environment.

[0003] In the relevant scenario technologies, many industrial parks have focused on the development of renewable energy such as wind power and photovoltaics, and explored sustainable development models to achieve energy self-sufficiency and green production by building park-level new energy projects. However, the intermittent and volatile nature of new energy such as wind power and photovoltaics makes it difficult to fully match the power load of the park, bringing new challenges to the energy management of the park. In order to improve the level of new energy consumption, many parks have adopted means such as energy storage system construction and load-side energy consumption mode adjustment. However, these methods are usually accompanied by high costs, including the construction and operation and maintenance costs of energy storage equipment, and indirect costs caused by load adjustment. For parks that are more sensitive to economic efficiency, excessively high new energy consumption targets may lead to a significant increase in costs and weaken the economic competitiveness of the park. On the contrary, when new energy is not fully absorbed, it may lead to the phenomenon of wind and light abandonment, which not only causes waste of resources, but also may lose policy support and affect economic benefits. In the relevant technologies, the low utilization rate of renewable energy causes waste, the resource cost is high, and the accuracy of the assessed new energy consumption capacity of the park is poor. Summary of the invention

[0004] The present invention provides a method, device and storage medium for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, so as to solve the defects in the prior art of waste caused by low utilization rate of renewable energy, high resource cost and poor accuracy of the evaluated new energy consumption capacity of the park, thereby improving the utilization rate of renewable resources, saving resource cost and greatly improving the accuracy of evaluating the new energy consumption capacity.

[0005] In a first aspect, the present invention provides a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, comprising the following steps.

[0006] Step 1: Based on the wind power and photovoltaic power generation constraints, thermal power unit operation constraints, and energy storage equipment operation constraints, a power generation model for different power generation resources in the park is constructed; Step 2: Based on the load demand response potential of the park, the upper-level consumption model is constructed with the maximum consumption as the objective function to adjust the consumption of new energy; Step 3: Based on the operation cost of thermal power units, the regulation cost of energy storage equipment and the load regulation cost, the lower-level cost model is constructed with the minimum total cost as the objective function; Step 4: Based on the power generation model, the upper-level consumption model and the lower-level cost model, the new energy consumption capacity of the park is evaluated.

[0007] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the operation constraints of the thermal power unit in step 1 are specifically: In the formula, is the output of thermal power units during period t, , are the upper and lower limits of thermal power unit output respectively. , are the upward climbing rate and the downward climbing rate respectively.

[0008] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the energy storage device operation constraints in step 1 are specifically: In the formula, is the state of charge, , are the charging power in period t and the discharging power in period t respectively, , are the charging efficiency and discharging efficiency of the energy storage device, respectively. , are the upper limit of the state of charge of the energy storage device and the lower limit of the state of charge of the energy storage device, respectively. , are the maximum charging power of the energy storage device in period t and the maximum discharging power of the energy storage device in period t respectively.

[0009] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the wind power and photovoltaic power generation constraints in step 1 are specifically: In the formula, , are wind power consumption and photovoltaic power consumption in period t, , are the predicted power generation of wind power and photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

[0010] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the constraint in step 1 also includes a load response constraint, and the load response constraint is specifically: In the formula, It's time The actual load that the power supply meets, It's time The upper limit of load that can be reduced, It is from time Transfer to time The maximum allowable load.

[0011] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the constraint in step 1 also includes a power balance constraint, and the power balance constraint is specifically: In the formula, is the power generation of the thermal power unit in period t, is the wind power consumption in period t, is the photovoltaic consumption in period t, , They are respectively the charging power of the energy storage in period t and the discharging power of the energy storage in period t. is the load during period t.

[0012] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, step 2 specifically includes: According to the load demand response potential of the park and the regulation of the energy storage equipment charging and discharging on the new energy consumption, an upper-level consumption model is constructed with the maximum total consumption as the objective function; The total absorption capacity is the sum of the wind power absorption capacity and the photovoltaic absorption capacity; The upper layer consumption model is specifically as follows: In the formula, is the proportional coefficient, reflecting the priority rate of wind power consumption and photovoltaic power consumption in the park, T is the total number of power load periods in the scenario, is the wind power consumed in period t, is the photovoltaic power consumed during period t.

[0013] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the uncertainty set U corresponding to the upper-layer consumption model is specifically: In the formula, , are the actual output of wind power in period t and the actual output of photovoltaic power in period t, , They are the predicted power generation of wind power in period t and the predicted power generation of photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

[0014] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, step 3 specifically includes: Determine the total cost according to the operating cost of the thermal power unit, the regulation cost of the energy storage device and the load regulation cost, and construct a lower-level cost model with the minimum total cost as the objective function; The operating cost of the thermal power unit at least includes the power generation cost and the start-up and shutdown cost of the thermal power unit; The energy storage device adjustment cost at least includes the charging aging cost and the discharging aging cost of the energy storage device; The load regulation cost includes at least the cost of production reduction caused by load regulation and the time cost of load recovery; The lower layer cost model is specifically: In the formula, is the operating cost of the thermal power unit, adjusting costs for said energy storage device, a cost for regulating the load; Among them, the operating cost of the thermal power unit Specifically: In the formula, is the power generation cost of thermal power units, is the start-up and shutdown cost of thermal power units, N is the number of thermal power units, , , is the thermal power fuel cost coefficient, is the output of the nth thermal power unit in period t, , are the startup cost and shutdown cost of thermal power unit n, It is a 0-1 variable, indicating the start and stop status of the thermal power unit; Among them, the energy storage equipment adjustment cost Specifically: In the formula, , They are the charging aging cost and discharging aging cost of the energy storage equipment, , are the charging power and discharging power of the energy storage device at time t respectively; The load regulation cost include: In the formula, Reduce costs per unit load, For Transfer to The unit load transfer cost.

[0015] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, step 4 comprises: Step 40: Based on the constraints corresponding to the power generation model, an improved optimization algorithm is used to perform two-stage robust optimization processing on the objective function of the upper-level consumption model and the objective function of the lower-level cost model to evaluate the new energy consumption capacity of the park; the optimization algorithm is an optimization algorithm composed of a genetic algorithm and a conjugate gradient algorithm.

[0016] Genetic algorithm: Genetic algorithm is a population-based search algorithm that imitates the genetic and natural selection mechanisms in the biological evolution process. It is suitable for global optimization problems and is particularly good at handling nonlinear and complex search problems.

[0017] Conjugate gradient algorithm: The conjugate gradient algorithm is an iterative optimization algorithm used to solve large-scale linear equations or quadratic optimization problems. It accelerates the gradient descent process by constructing conjugate directions.

[0018] Advantages of genetic algorithms: strong global search capabilities, not prone to falling into local optimality; suitable for complex and nonlinear problems.

[0019] Advantages of the conjugate gradient algorithm: fast convergence, especially for large-scale sparse problems; no need to store the Hessian matrix, saving memory.

[0020] Genetic algorithm and conjugate gradient algorithm can be used together to form a hybrid algorithm. For example, first use the genetic algorithm to perform a global search to find the potential optimal area, and then use the conjugate gradient algorithm to perform a fine search in this area to improve the efficiency and accuracy of the solution. This hybrid strategy makes full use of the global search capability of the genetic algorithm and the fast convergence of the conjugate gradient algorithm.

[0021] The step 40 specifically includes: Step 41: Based on the constraints of the main problem, a dynamically adjusted optimization strategy is used to solve the upper bound of the objective function of the upper-level consumption model. To ensure the feasibility and optimization efficiency of the solution of the objective function of the upper-level consumption model; the main problem is an optimization problem for solving the objective function of the upper-level consumption model in the first stage of the two-stage robust optimization process; the constraint conditions of the main problem are the constraints of different power generation resources corresponding to the power generation model; Step 42: Substitute the optimization result of the main problem into the sub-problem, and solve the lower bound of the objective function of the lower cost model through scenario generation and deviation adjustment strategy. , to simulate the worst case in a complex scenario; the sub-problem is an optimization problem for solving the objective function of the lower-level cost model in the second stage of the two-stage robust optimization; Step 43: Calculate the upper bound and the lower bound The difference between them is used to determine whether the current solution meets the global optimality requirement, so as to ensure the accuracy and robustness of the model; Step 44: If the upper bound and the lower bound If the difference between the two does not meet the global optimality requirement, then constraints and variables are added to the main problem based on the scenario generated by the sub-problem, and the model structure is adjusted and then solved again until the termination condition is met to obtain the global optimal solution; Or, if the upper bound and the lower bound If the difference between them meets the global optimality requirement, the current solution is the global optimal solution, and the new energy absorption capacity of the park is evaluated based on the global optimal solution.

[0022] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, step 41 specifically includes: While maximizing the total absorption of wind power and photovoltaic power, the scenario synergy factor is dynamically introduced. , by dynamically adjusting Weight allocation, and combined with the constraints of the main problem, solve the upper bound of the objective function of the upper-level consumption model : Among them, the upper bound The specific calculation formula is: in, is the historical deviation coefficient, which is used to quantify the deviation between the actual power generation of historical wind power and photovoltaic power and the predicted power generation; It is the scene coupling strength, which reflects the correlation between the current scene and the historical scene, or the correlation between the current scene and the predicted scene; is the number of historical samples; For scene collection; is the current scene feature vector, including ; for scene similarity; for The weight of .

[0023] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, step 42 specifically includes: Substitute the decision variables obtained from the main problem into the subproblem, so that the subproblem can simulate the worst power generation scenario under the wind power and photovoltaic power generation forecast deviation, adjust the power generation forecast value based on the scenario deviation, and calculate the power generation of the worst scenario and ; If the sub-problem corresponding to the current worst scenario has no solution, a set of alternative scenarios are randomly generated to add new variables and new constraints to the main problem; If the subproblem corresponding to the current worst scenario has a solution, then solve the subproblem and obtain the lower bound of the objective function ; The power generation in the worst scenario is and Specifically: in, It is scene bias; is the historical error data; It is the uncertainty bias based on the prediction of probability distribution; is the historical error mean; is the historical error variance.

[0024] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the upper bound in step 43 is and the lower bound The specific calculation formula for the difference between is: in, It is a dynamic penalty factor, reflecting the degree of uncertainty of the scene.

[0025] If satisfied , the current solution is the optimal solution, and the calculation ends; if it does not satisfy , execute step 44.

[0026] Preferably, according to a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention, the scenario generated based on the sub-problem in step 44 adds constraints and variables to the main problem and adjusts the model structure specifically including: Based on the sub-problems, the current worst scenario and the historical scenario deviations, the distribution of the scenario generator is dynamically adjusted to generate new optimization constraints, and the new optimization constraints are returned to step 41 to continue iterative solution until the termination condition is met to obtain the global optimal solution.

[0027] In a second aspect, the present invention further provides a device for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, comprising the following modules: Construct a power generation model module, which is used to construct power generation models of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints, and energy storage equipment operation constraints; Construct an upper-level consumption model module to adjust the consumption of new energy based on the load demand response potential of the park, and construct an upper-level consumption model with the maximum consumption as the objective function; Construct a lower-level cost model module, which is used to construct a lower-level cost model based on the operating cost of the thermal power unit, the regulation cost of the energy storage equipment and the load regulation cost, with the minimum total cost as the objective function; The module for evaluating the new energy consumption capacity is used to evaluate the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model.

[0028] In a third aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error as described in any one of the above-mentioned methods.

[0029] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for evaluating the new energy consumption capacity of a park based on power generation costs and prediction errors as described in any of the above-mentioned methods.

[0030] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for evaluating the new energy consumption capacity of a park based on power generation costs and prediction errors.

[0031] The present invention provides a method, device and storage medium for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, through step 1: constructing a power generation model of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; step 2: adjusting the new energy consumption based on the load demand response potential of the park, and constructing an upper-level consumption model with the maximum consumption as the objective function; step 3: constructing a lower-level cost model with the minimum total cost as the objective function according to the thermal power unit operation cost, energy storage equipment adjustment cost and load adjustment cost; step 4: evaluating the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model. It is used to solve the defects of the prior art that the utilization rate of renewable energy is low, the resource cost is high, and the accuracy of the evaluated new energy consumption capacity of the park is poor, so as to improve the utilization rate of renewable resources, save resource costs, and greatly improve the accuracy of evaluating the new energy consumption capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a flow chart of a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention.

[0034] Figure 2 It is a flow chart of a two-stage robust optimization method using an improved C&CG algorithm provided by the present invention.

[0035] Figure 3 It is a structural schematic diagram of a device for evaluating the park's new energy consumption capacity based on power generation cost and prediction error provided by the present invention.

[0036] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] First, several nouns involved in the present invention are analyzed: Consumption: refers to the process in the power system whereby the electricity generated by a power plant is transmitted and distributed to end users and actually used. It describes the entire process of electricity from a power plant through transmission and distribution to end users (such as households, factories, commercial units, etc.) and actually used. In other words, power consumption refers to the activity of converting electricity into other forms of energy (such as heat energy, mechanical energy, etc.) at the terminal. Operational constraints: Power system operational constraints (AGC) are an important technical means to ensure the balance between power generation and load and maintain the frequency quality of the power system at all times.

[0039] Prediction error: refers to the difference between the predicted result and the actual result, which reflects the accuracy of the prediction. In the optimization of power system, the analysis of prediction error is crucial to improving the new energy absorption capacity and optimizing the dispatch plan.

[0040] C&CG algorithm: Column and Constraint Generation algorithm is a method specifically used to solve linear programming problems with a large number of variables and constraints. In power system optimization, C&CG algorithm is widely used in economic dispatch, unit combination, renewable energy integration and other issues. For example, by considering the uncertainty and volatility of wind and solar power generation, as well as the operating characteristics of thermal power and energy storage, C&CG algorithm can help formulate reasonable dispatch plans and promote the efficient use of new energy.

[0041] Robust optimization: is a type of mathematical programming problem that takes into account parameter uncertainty. It is a relatively high-level method in operations research. In recent years, research on robust optimization has become increasingly popular. Common robust optimization problems include basic robust optimization, multi-stage robust optimization, distributed robust optimization, etc. Robust optimization aims to deal with the challenges of parameter uncertainty in optimization problems, and is committed to optimizing the solution under the worst case or the solution under the worst parameter distribution (corresponding to distributed robust optimization), so that the final solution has a very strong ability to resist uncertainty or risk.

[0042] Two-stage robust optimization problem: It is a special case of multi-stage robust optimization. In a two-stage robust optimization problem, it generally contains two different levels of decision variables, also known as the first-stage decision and the second-stage decision.

[0043] In the related art, there are at least the following technical problems: How to find a balance between the new energy consumption rate and economy has become an urgent problem to be solved in the process of green energy transformation of the park.

[0044] Combine the following Figure 1-Figure 4 The present invention describes a method, device and storage medium for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, which is used to solve the defects of the prior art that the low utilization rate of renewable energy causes waste, the resource cost is high, and the accuracy of the evaluated new energy consumption capacity of the park is poor, thereby improving the utilization rate of renewable resources, saving resource costs, and greatly improving the accuracy of evaluating the new energy consumption capacity. It can also provide scientific decision-making support for the park, optimize the relationship between new energy consumption and economy, and promote the efficient use of renewable energy and the sustainable development of the park.

[0045] Figure 1 This is a flow chart of a method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error provided by the present invention. Figure 1 As shown, the method may include but is not limited to S1 to S4: Step 1 (S1): construct a power generation model for different power generation resources in the park based on wind power and photovoltaic power generation constraints, thermal power unit operation constraints, and energy storage equipment operation constraints; Specifically, constraints such as thermal power unit operation constraints, energy storage equipment operation constraints, load response constraints, wind power and photovoltaic power generation constraints (wind power and photovoltaic consumption constraints) and electricity balance constraints are used to construct an independent industrial park equipment operation model.

[0046] Furthermore, the operation constraints of the thermal power unit may specifically be: In the formula, is the output of thermal power units during period t, , are the upper and lower limits of thermal power unit output respectively. , are the upward climbing rate and the downward climbing rate respectively.

[0047] Furthermore, the energy storage equipment operation constraints are as follows: In the formula, is the state of charge, , are the charging power in period t and the discharging power in period t respectively, , are the charging efficiency and discharging efficiency of the energy storage device, respectively. , are the upper limit of the state of charge of the energy storage device and the lower limit of the state of charge of the energy storage device, respectively. , are the maximum charging power of the energy storage device in period t and the maximum discharging power of the energy storage device in period t respectively.

[0048] Furthermore, the wind and photovoltaic power generation constraints are as follows: In the formula, , are wind power consumption and photovoltaic power consumption in period t, , are the predicted power generation of wind power and photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

[0049] Furthermore, the load response constraints are specifically: In the formula, It's time The actual load that the power supply meets, It's time The upper limit of load that can be reduced, It is from time Transfer to time The maximum allowable load.

[0050] Furthermore, the power balance constraint is specifically: In the formula, is the power generation of the thermal power unit in period t, is the wind power consumption in period t, is the photovoltaic consumption in period t, , They are respectively the charging power of the energy storage in period t and the discharging power of the energy storage in period t. is the load during period t.

[0051] In some embodiments of the present invention, the wind power and photovoltaic power generation constraints are: Uncertainty and volatility: Wind power and photovoltaic power generation are greatly affected by meteorological conditions, and their output is random and intermittent.

[0052] Forecasting output: To deal with this uncertainty, it is usually necessary to forecast the output of wind and photovoltaic power generation and consider these forecast values ​​in the model.

[0053] Absorption capacity: When optimizing scheduling, it is necessary to consider the system's new energy absorption capacity, that is, how much new energy the system can absorb without violating any constraints.

[0054] Furthermore, the thermal power unit operation constraints are: Basic peak load regulation stage: The output range of thermal power units is usually between their rated output and minimum technical output.

[0055] Deep peak load regulation stage: As the installed capacity of wind power and photovoltaic power generation expands, thermal power units may need to operate below their minimum technical output, which will increase coal consumption and may lead to higher fuel costs.

[0056] Ramp rate: The output power change rate of the thermal power unit is limited by the ramp rate.

[0057] Pollutant penalty costs: The operation of thermal power units will also produce pollutants, such as SO2, NOx and dust. The emission of these pollutants also needs to consider the corresponding penalty costs.

[0058] Furthermore, the energy storage equipment operation constraints are: State of Charge (SOC): The SOC of an energy storage device needs to vary within a specified range to ensure its effective operation.

[0059] Charging and discharging efficiency: There is energy loss in the charging and discharging process of energy storage devices, which will affect its actual available capacity.

[0060] Maximum charge and discharge power: The charge and discharge power of energy storage equipment has an upper and lower limit and cannot exceed its design capacity.

[0061] Operating costs: The operating costs of energy storage equipment include investment costs, depreciation costs, and possible battery replacement costs.

[0062] In summary, in power system optimization, it is crucial to reasonably consider and handle the constraints of wind power and photovoltaic power generation, thermal power unit operation constraints, and energy storage equipment operation constraints to achieve economic, efficient, and stable power supply. Through accurate models and algorithms, the utilization efficiency of new energy can be maximized while ensuring the reliability and economy of the power system.

[0063] Step 2 (S2): Based on the load demand response potential of the park, the upper-level consumption model is constructed with the maximum consumption as the objective function to adjust the consumption of new energy.

[0064] It is understandable that based on the impact of load demand response potential on new energy consumption, the upper-level consumption model is constructed with the maximum consumption as the objective function, including: According to the load demand response potential of the park and the regulation of the energy storage equipment charging and discharging on the new energy consumption, an upper-level consumption model is constructed with the maximum total consumption as the objective function; The total absorption capacity is the sum of the wind power absorption capacity and the photovoltaic absorption capacity; The upper layer consumption model is specifically as follows: In the formula, is the proportional coefficient, reflecting the priority rate of wind power consumption and photovoltaic power consumption in the park, T is the total number of power load periods in the scenario, is the wind power consumed in period t, is the photovoltaic power consumed during period t.

[0065] Furthermore, the uncertainty set U corresponding to the layer absorption model is specifically: In the formula, , are the actual output of wind power in period t and the actual output of photovoltaic power in period t, , They are the predicted power generation of wind power in period t and the predicted power generation of photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

[0066] Step 3 (S3): According to the operation cost of thermal power units, the regulation cost of energy storage equipment and the load regulation cost, a lower-level cost model is constructed with the minimum total cost as the objective function.

[0067] The total cost is determined according to the operating cost of the thermal power unit, the regulation cost of the energy storage device and the load regulation cost, and a lower-level cost model is constructed with the minimum total cost as the objective function.

[0068] Furthermore, the operating cost of the thermal power unit at least includes the power generation cost and the start-up and shutdown cost of the thermal power unit.

[0069] Furthermore, the energy storage device adjustment cost at least includes a charging aging cost and a discharging aging cost of the energy storage device.

[0070] Furthermore, the load regulation cost includes at least the cost of production reduction caused by load regulation and the time cost of load recovery.

[0071] It can be further understood that the lower-level cost model is specifically: In the formula, is the operating cost of the thermal power unit, adjusting costs for said energy storage device, is the load regulation cost.

[0072] Among them, the operating cost of the thermal power unit Specifically: In the formula, is the power generation cost of thermal power units, is the start-up and shutdown cost of thermal power units, N is the number of thermal power units, , , is the thermal power fuel cost coefficient, is the output of the nth thermal power unit in period t, , are the startup cost and shutdown cost of thermal power unit n, It is a 0-1 variable, indicating the start and stop status of the thermal power unit.

[0073] Among them, the energy storage equipment adjustment cost Specifically: In the formula, , They are the charging aging cost and discharging aging cost of the energy storage equipment, , are the charging power and discharging power of the energy storage device at time t respectively.

[0074] The load regulation cost include: In the formula, Reduce costs per unit load, For Transfer to The unit load transfer cost.

[0075] Step 4 (S4): Based on the power generation model, the upper-level consumption model and the lower-level cost model, the new energy consumption capacity of the park is evaluated.

[0076] Step 40: Based on the constraints corresponding to the power generation model, the objective function of the upper-layer consumption model and the objective function of the lower-layer cost model are solved by a two-stage robust optimization process using an improved optimization algorithm to evaluate the new energy consumption capacity of the park; the optimization algorithm is an optimization algorithm composed of a genetic algorithm and a conjugate gradient algorithm; The improved C&CG algorithm is used to solve the two-stage robust optimization, that is, the objective function of the upper-level consumption model and the objective function of the lower-level cost model are solved using an improved optimization algorithm composed of a genetic algorithm and a conjugate gradient algorithm to obtain the optimal solution.

[0077] The improved C&CG algorithm can generate multiple scenarios and optimize them by considering the uncertainty of renewable energy output, thereby obtaining a more robust optimization solution.

[0078] Furthermore, if Figure 2 As shown, the step 40 specifically includes the following steps: Step 41: Based on the constraints of the main problem, a dynamically adjusted optimization strategy is used to solve the upper bound of the objective function of the upper-level consumption model. To ensure the feasibility and optimization efficiency of the solution of the objective function of the upper-level consumption model; the main problem is an optimization problem for solving the objective function of the upper-level consumption model in the first stage of the two-stage robust optimization process; the constraint conditions of the main problem are the constraints of different power generation resources corresponding to the power generation model; Step 42: Substitute the optimization result of the main problem into the sub-problem, and solve the lower bound of the objective function of the lower cost model through scenario generation and deviation adjustment strategy. , to simulate the worst case in a complex scenario; the sub-problem is an optimization problem for solving the objective function of the lower-level cost model in the second stage of the two-stage robust optimization; Step 43: Calculate the upper bound of the objective function and the lower bound The difference between them is used to determine whether the current solution meets the global optimality requirement, so as to ensure the accuracy and robustness of the model; Step 44: If the upper bound and the lower bound If the difference between the two does not meet the global optimality requirement, then constraints and variables are added to the main problem based on the scenario generated by the sub-problem, and the model structure is adjusted and then solved again until the termination condition is met to obtain the global optimal solution; Or, if the upper bound and the lower bound If the difference between them meets the global optimality requirement, the current solution is the global optimal solution, and the new energy absorption capacity of the park is evaluated based on the global optimal solution.

[0079] In some embodiments of the present invention, the C&CG algorithm, i.e., the Column and Constraint Generation algorithm, is an effective method for solving large-scale linear programming problems. It gradually approaches the optimal solution of the problem by iteratively adding columns or constraints that violate optimality. The two-stage robust optimization is a method for dealing with uncertain optimization problems, in which the first stage determines the robust values ​​of decision variables, and the second stage adjusts the strategy to cope with uncertainty based on these decision variables.

[0080] The improved C&CG algorithm is optimized on the basis of the traditional C&CG algorithm to improve the efficiency and accuracy of the solution. Such improvements may include more efficient column / constraint generation strategies, more sophisticated iteration stopping criteria, and customized algorithm design for specific problem structures. In the two-stage robust optimization, the improved C&CG algorithm is used to solve the main problem and sub-problems respectively.

[0081] In some embodiments of the present invention, in the two-stage robust optimization, the master problem is usually a deterministic optimization problem, which determines the decision variables of the first stage. When solving the master problem using the improved C&CG algorithm, the following steps can be followed: 1. Initialization: set the initial solution and initial upper bound.

[0082] 2. Column / constraint generation: Based on the current solution, generate columns or constraints that violate optimality and add them to the restricted master problem.

[0083] 3. Solve the restricted master problem: Use the linear programming solver to solve the restricted master problem after adding the new columns / constraints.

[0084] 4. Check convergence: Determine whether the current solution meets the convergence criteria (such as the change in the objective function value is less than the preset threshold). If so, output the optimal solution; otherwise, return to step 2 to continue iterating.

[0085] Furthermore, the sub-problem is an optimization problem based on the decision variables determined by the main problem, taking into account uncertainty factors. It is usually one or more stochastic optimization problems used to evaluate the performance of the system under given decisions. When using the improved C&CG algorithm to solve sub-problems, the following points should be noted: Sample generation: Generate enough sample scenarios based on the probability distribution of uncertainty factors.

[0086] Scenario optimization: For each sample scenario, solve the corresponding optimization problem (this may involve using the C&CG algorithm again or other optimization methods).

[0087] Performance evaluation: Based on the optimization results in all scenarios, the overall performance of the system under uncertainty is evaluated.

[0088] Feedback adjustment: If necessary, adjust the decision variables of the main problem based on the solutions to the subproblems and re-solve the main problem.

[0089] In some embodiments of the present invention, step 41 uses a dynamically adjusted optimization strategy to solve the upper bound of the objective function of the upper-level consumption model based on the constraints of the main problem. To ensure the feasibility and optimization efficiency of the solution of the objective function of the upper-level consumption model, specifically include: While maximizing the total absorption of wind power and photovoltaic power, the scenario synergy factor is dynamically introduced. , by dynamically adjusting Weight allocation, and combined with the constraints of the main problem, solve the upper bound of the objective function of the upper-level consumption model .

[0090] Among them, the upper bound The specific calculation formula is: in, is the historical deviation coefficient, which is used to quantify the deviation between the actual power generation of historical wind power and photovoltaic power and the predicted power generation; It is the scene coupling strength, which reflects the correlation between the current scene and the historical scene, or the correlation between the current scene and the predicted scene; is the number of historical samples; For scene collection; is the current scene feature vector, including ; for scene similarity; for The weight of .

[0091] It should be further explained that the main problem is to solve the objective function of the upper-layer consumption model in the first stage of the two-stage robust optimization process.

[0092] The constraints of the main problem are the constraints of different power generation resources corresponding to the power generation model, which may include but are not limited to thermal power unit operation constraints, energy storage equipment operation constraints, load response constraints, wind power and photovoltaic power generation constraints (wind power and photovoltaic consumption constraints) and power balance constraints.

[0093] In some embodiments of the present invention, step 42 substitutes the optimization result of the main problem into the sub-problem, and solves the lower bound of the objective function of the lower cost model through scenario generation and deviation adjustment strategy. , to simulate the worst-case scenario in complex scenarios, including: Substitute the decision variables obtained from the main problem into the subproblem, so that the subproblem can simulate the worst power generation scenario under the wind power and photovoltaic power generation forecast deviation, adjust the power generation forecast value based on the scenario deviation, and calculate the power generation of the worst scenario and .

[0094] If the sub-problem corresponding to the current worst scenario has no solution, a set of alternative scenarios are randomly generated to add new variables and new constraints to the main problem.

[0095] If the subproblem corresponding to the current worst scenario has a solution, then solve the subproblem and obtain the lower bound of the objective function .

[0096] The power generation in the worst scenario is and Specifically: in, It is scene bias; is the historical error data; It is the uncertainty bias based on the prediction of probability distribution; is the historical error mean; is the historical error variance.

[0097] It should be noted that the sub-problem is an optimization problem for solving the objective function of the lower-level cost model in the second stage of the two-stage robust optimization.

[0098] In some embodiments of the present invention, the upper bound in step 43 and the lower bound The specific calculation formula for the difference between is: in, It is a dynamic penalty factor, reflecting the degree of uncertainty of the scene.

[0099] If satisfied , the current solution is the optimal solution, and the calculation ends; if it does not satisfy , execute step 44, where ò is the parameter threshold required for global optimality.

[0100] In some embodiments of the present invention, adding constraints and variables to the main problem based on the scenario generated by the sub-problem in step 44 and adjusting the model structure specifically include: Based on the sub-problems, the current worst scenario and the historical scenario deviations, the distribution of the scenario generator is dynamically adjusted to generate new optimization constraints, and the new optimization constraints are returned to step 41 to continue iterative solution until the termination condition is met to obtain the global optimal solution.

[0101] In some embodiments of the present invention, in power system optimization, the improved C&CG algorithm gradually approaches the optimal solution of the problem by iteratively adding columns or constraints that violate optimality. When the difference between the upper bound and the lower bound does not meet the global optimality requirement, constraints and variables are added to the main problem based on the scenario generated by the subproblem, and the model structure is adjusted and the problem is solved again until the termination condition is met to obtain the global optimal solution.

[0102] If the difference between the upper bound and the lower bound meets the global optimality requirement, the current solution is the global optimal solution, and the new energy consumption capacity of the park is evaluated based on this global optimal solution. This process ensures the feasibility and optimization efficiency of the solution while taking into account the uncertainty and complexity of the power system.

[0103] In some embodiments of the present invention, the following is another understanding of steps S1 to S4: Going further, build a power generation model: It is necessary to consider the uncertainty and volatility of wind and solar power generation, as well as the operating characteristics of thermal power and energy storage.

[0104] Wind and solar power generation is affected by meteorological conditions and is subject to randomness and uncertainty, which needs to be handled through probabilistic models or scenario analysis.

[0105] Thermal power units need to consider technical constraints such as their ramp rate and minimum stable output.

[0106] The energy storage system needs to consider factors such as its charging and discharging efficiency, capacity limitations and state transitions.

[0107] Furthermore, we construct an upper-level consumption model: Load demand response potential refers to the ability of users to adjust their electricity consumption behavior based on price signals or incentive mechanisms.

[0108] The ability to absorb new energy not only depends on the supply capacity of the power generation side, but is also affected by user demand.

[0109] The upper-level model takes the maximum absorption capacity as its objective function, which means maximizing the utilization efficiency of new energy (such as wind energy and solar energy).

[0110] Going further, build the lower-level cost model: The cost of power generation includes fuel cost, operation and maintenance cost, etc.

[0111] Energy storage costs involve investment costs, depreciation costs, operation and maintenance costs, and possible battery replacement costs.

[0112] Load regulation costs may include the costs of demand-side management, such as incentive payments to customers who participate in demand response.

[0113] The objective function of minimizing the total cost requires achieving economic optimality while satisfying all operating constraints.

[0114] Furthermore, the improved C&CG algorithm is used to solve: The C&CG algorithm is an efficient method for solving large-scale mixed-integer linear programming problems.

[0115] Improved C&CG algorithms may include more sophisticated column generation strategies, faster convergence speed, or other optimization techniques.

[0116] By iteratively adding columns or constraints that violate optimality, the C&CG algorithm gradually approaches the global optimal solution.

[0117] In general, through the above steps, we can get the new energy absorption capacity, that is, how much new energy the power system can absorb under certain conditions without violating any constraints. This helps power system operators to formulate reasonable dispatch plans and promote the efficient use of new energy.

[0118] The present invention provides a method, device and storage medium for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, through step 1: constructing a power generation model of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; step 2: adjusting the new energy consumption based on the load demand response potential of the park, and constructing an upper-level consumption model with the maximum consumption as the objective function; step 3: constructing a lower-level cost model with the minimum total cost as the objective function according to the thermal power unit operation cost, energy storage equipment adjustment cost and load adjustment cost; step 4: evaluating the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model. It is used to solve the defects of the prior art that the utilization rate of renewable energy is low, the resource cost is high, and the accuracy of the evaluated new energy consumption capacity of the park is poor, so as to improve the utilization rate of renewable resources, save resource costs, and greatly improve the accuracy of evaluating the new energy consumption capacity.

[0119] The following is a description of the device for evaluating the park's new energy consumption capacity based on power generation cost and prediction error provided by the present invention. The device for evaluating the park's new energy consumption capacity based on power generation cost and prediction error described below and the method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error described above can refer to each other and will not be repeated here.

[0120] like Figure 3 The figure shows a schematic diagram of the structure of a new energy consumption capacity evaluation device for a park based on power generation cost and prediction error provided by the present invention. A new energy consumption capacity evaluation device for a park based on power generation cost and prediction error includes the following modules: A power generation model building module 310 is used to build power generation models of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; Constructing an upper-layer consumption model module 320, which is used to adjust the consumption of new energy based on the load demand response potential of the park, and constructing an upper-layer consumption model with the maximum consumption as the objective function; A lower-level cost model building module 330 is used to build a lower-level cost model based on the operation cost of the thermal power unit, the regulation cost of the energy storage device and the load regulation cost, with the minimum total cost as the objective function; The module 340 for evaluating the new energy consumption capacity is used to evaluate the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model.

[0121] The present invention provides a method, device and storage medium for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, through step 1: constructing a power generation model of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; step 2: adjusting the new energy consumption based on the load demand response potential of the park, and constructing an upper-level consumption model with the maximum consumption as the objective function; step 3: constructing a lower-level cost model with the minimum total cost as the objective function according to the thermal power unit operation cost, energy storage equipment adjustment cost and load adjustment cost; step 4: evaluating the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model. It is used to solve the defects of the prior art that the utilization rate of renewable energy is low, the resource cost is high, and the accuracy of the evaluated new energy consumption capacity of the park is poor, so as to improve the utilization rate of renewable resources, save resource costs, and greatly improve the accuracy of evaluating the new energy consumption capacity.

[0122] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the evaluation method of the new energy consumption capacity of the park based on the power generation cost and the prediction error, the method comprising: step 1: constructing the power generation model of different power generation resources in the park according to the wind power and photovoltaic power generation constraints, the operation constraints of the thermal power unit and the operation constraints of the energy storage device; step 2: regulating the new energy consumption based on the load demand response potential of the park, constructing the upper-level consumption model with the maximum consumption as the objective function; step 3: constructing the lower-level cost model with the minimum total cost as the objective function according to the operation cost of the thermal power unit, the regulation cost of the energy storage device and the load regulation cost; step 4: evaluating the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model.

[0123] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0124] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the park's new energy consumption capacity evaluation method based on power generation cost and prediction error provided by the above methods, the method comprising: Step 1: Constructing a power generation model of different power generation resources in the park based on wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; Step 2: Based on the load demand response potential of the park, the upper-level consumption model is constructed with the maximum consumption as the objective function to adjust the new energy consumption; Step 3: Based on the operating cost of the thermal power unit, the energy storage equipment regulation cost and the load regulation cost, a lower-level cost model is constructed with the minimum total cost as the objective function; Step 4: Based on the power generation model, the upper-level consumption model and the lower-level cost model, the new energy consumption capacity of the park is evaluated.

[0125] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error provided by the above-mentioned methods, the method comprising: Step 1: constructing a power generation model for different power generation resources in the park based on wind power and photovoltaic power generation constraints, thermal power unit operation constraints and energy storage equipment operation constraints; Step 2: regulating the new energy consumption based on the load demand response potential of the park, and constructing an upper-level consumption model with the maximum consumption as the objective function; Step 3: constructing a lower-level cost model with the minimum total cost as the objective function based on the operating cost of the thermal power unit, the energy storage equipment regulation cost and the load regulation cost; Step 4: evaluating the park's new energy consumption capacity based on the power generation model, the upper-level consumption model and the lower-level cost model.

[0126] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, characterized in that: The following steps are involved: Step 1: Based on the wind power and photovoltaic power generation constraints, thermal power unit operation constraints, and energy storage equipment operation constraints, a power generation model for different power generation resources in the park is constructed; Step 2: Based on the load demand response potential of the park, the upper-level consumption model is constructed with the maximum consumption as the objective function to adjust the consumption of new energy; Step 3: Based on the operation cost of thermal power units, the regulation cost of energy storage equipment and the load regulation cost, the lower-level cost model is constructed with the minimum total cost as the objective function; Step 4: Based on the power generation model, the upper-level consumption model and the lower-level cost model, the new energy consumption capacity of the park is evaluated.

2. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 1 is characterized in that: The operation constraints of the thermal power unit in step 1 are specifically: In the formula, is the output of thermal power units during period t, , are the upper and lower limits of thermal power unit output respectively. , are the upward climbing rate and the downward climbing rate respectively.

3. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 1 is characterized in that: The energy storage device operation constraints in step 1 are specifically: In the formula, is the state of charge, , are the charging power in period t and the discharging power in period t respectively, , are the charging efficiency and discharging efficiency of the energy storage device, respectively. , are the upper limit of the state of charge of the energy storage device and the lower limit of the state of charge of the energy storage device, respectively. , are the maximum charging power of the energy storage device in period t and the maximum discharging power of the energy storage device in period t respectively.

4. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 1 is characterized in that: The wind and photovoltaic power generation constraints in step 1 are specifically: In the formula, , are the wind power consumption and photovoltaic power consumption in period t, , are the predicted power generation of wind power and photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

5. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 1 is characterized in that: The constraints in step 1 also include load response constraints, which are specifically: In the formula, It's time The actual load that the power supply meets, It's time The upper limit of load that can be reduced, It is from time Transfer to time The maximum allowable load.

6. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 1 is characterized in that: The constraints in step 1 also include power balance constraints, which are specifically: In the formula, is the power generation of the thermal power unit in period t, is the wind power consumption in period t, is the photovoltaic consumption in period t, , They are respectively the charging power of the energy storage in period t and the discharging power of the energy storage in period t. is the load during period t.

7. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 4 is characterized in that: The step 2 specifically includes: According to the load demand response potential of the park and the regulation of the energy storage equipment charging and discharging on the new energy consumption, an upper-level consumption model is constructed with the maximum total consumption as the objective function; The total absorption capacity is the sum of the wind power absorption capacity and the photovoltaic absorption capacity; The upper layer consumption model is specifically as follows: In the formula, is the proportional coefficient, reflecting the priority rate of wind power consumption and photovoltaic power consumption in the park, T is the total number of power load periods in the scenario, is the wind power consumed in period t, is the photovoltaic power consumed during period t.

8. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 7 is characterized in that: The uncertainty set U corresponding to the upper-level absorption model is specifically: In the formula, , are the actual output of wind power in period t and the actual output of photovoltaic power in period t, , They are the predicted power generation of wind power in period t and the predicted power generation of photovoltaic power in period t, , They are the deviation between the actual wind power generation and the predicted power generation, and the deviation between the actual photovoltaic power generation and the predicted power generation. , , , It is a 0-1 variable.

9. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 2 is characterized in that: The step 3 specifically includes: Determine the total cost according to the operating cost of the thermal power unit, the regulation cost of the energy storage device and the load regulation cost, and construct a lower-level cost model with the minimum total cost as the objective function; The operating cost of the thermal power unit at least includes the power generation cost and the start-up and shutdown cost of the thermal power unit; The energy storage device adjustment cost at least includes the charging aging cost and the discharging aging cost of the energy storage device; The load regulation cost includes at least the cost of production reduction caused by load regulation and the time cost of load recovery; The lower layer cost model is specifically: In the formula, is the operating cost of the thermal power unit, adjusting costs for said energy storage device, a cost for regulating the load; Among them, the operating cost of the thermal power unit Specifically: In the formula, is the power generation cost of the thermal power unit, is the start-up and shutdown cost of thermal power units, N is the number of thermal power units, , , is the thermal power fuel cost coefficient, is the output of the nth thermal power unit in period t, , are the startup cost and shutdown cost of thermal power unit n, It is a 0-1 variable, indicating the start and stop status of the thermal power unit; Among them, the energy storage equipment adjustment cost Specifically: In the formula, , They are the charging aging cost and discharging aging cost of the energy storage equipment, , are the charging power and discharging power of the energy storage device at time t respectively; The load regulation cost include: In the formula, Reduce costs per unit load, For Transfer to The unit load transfer cost.

10. The method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error according to any one of claims 1 to 9, characterized in that: The step 4 comprises: Step 40: Based on the constraints corresponding to the power generation model, the objective function of the upper-layer consumption model and the objective function of the lower-layer cost model are solved by a two-stage robust optimization process using an improved optimization algorithm to evaluate the new energy consumption capacity of the park; the optimization algorithm is an optimization algorithm composed of a genetic algorithm and a conjugate gradient algorithm; The step 40 specifically includes: Step 41: Based on the constraints of the main problem, a dynamically adjusted optimization strategy is used to solve the upper bound of the objective function of the upper-level consumption model. To ensure the feasibility and optimization efficiency of the solution of the objective function of the upper-level consumption model; the main problem is an optimization problem for solving the objective function of the upper-level consumption model in the first stage of the two-stage robust optimization process; the constraint conditions of the main problem are the constraints of different power generation resources corresponding to the power generation model; Step 42: Substitute the optimization result of the main problem into the sub-problem, and solve the lower bound of the objective function of the lower cost model through scenario generation and deviation adjustment strategy. , to simulate the worst case in a complex scenario; the sub-problem is an optimization problem for solving the objective function of the lower-level cost model in the second stage of the two-stage robust optimization; Step 43: Calculate the upper bound and the lower bound The difference between them is used to determine whether the current solution meets the global optimality requirement, so as to ensure the accuracy and robustness of the model; Step 44: If the upper bound and the lower bound If the difference between the two does not meet the global optimality requirement, then constraints and variables are added to the main problem based on the scenario generated by the sub-problem, and the model structure is adjusted and then solved again until the termination condition is met to obtain the global optimal solution; Or, if the upper bound and the lower bound If the difference between them meets the global optimality requirement, the current solution is the global optimal solution, and the new energy absorption capacity of the park is evaluated based on the global optimal solution.

11. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 10, characterized in that: The step 41 specifically includes: While maximizing the total absorption of wind power and photovoltaic power, the scenario synergy factor is dynamically introduced. , by dynamically adjusting Weight allocation, and combined with the constraints of the main problem, solve the upper bound of the objective function of the upper-level consumption model : Among them, the upper bound The specific calculation formula is: in, is the historical deviation coefficient, which is used to quantify the deviation between the actual power generation of historical wind power and photovoltaic power and the predicted power generation; It is the scene coupling strength, which reflects the correlation between the current scene and the historical scene, or the correlation between the current scene and the predicted scene; is the number of historical samples; For scene collection; is the current scene feature vector, including ; for scene similarity; for The weight of .

12. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 11, characterized in that: The step 42 specifically includes: Substitute the decision variables obtained from the main problem into the subproblem, so that the subproblem can simulate the worst power generation scenario under the wind power and photovoltaic power generation forecast deviation, adjust the power generation forecast value based on the scenario deviation, and calculate the power generation of the worst scenario and ; If the sub-problem corresponding to the current worst scenario has no solution, a set of alternative scenarios are randomly generated to add new variables and new constraints to the main problem; If the subproblem corresponding to the current worst scenario has a solution, then solve the subproblem and obtain the lower bound of the objective function ; The power generation in the worst scenario is and Specifically: in, It is scene bias; is the historical error data; It is the uncertainty bias based on the prediction of probability distribution; is the historical error mean; is the historical error variance.

13. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 12, characterized in that: The upper bound in step 43 and the lower bound The specific calculation formula for the difference between is: in, is a dynamic penalty factor, reflecting the degree of uncertainty of the scenario; If satisfied , the current solution is the optimal solution, and the calculation ends; if it does not satisfy , execute step 44.

14. The method for evaluating the park's new energy consumption capacity based on power generation cost and prediction error according to claim 13, characterized in that: The step 44 of adding constraints and variables to the main problem based on the scenario generated by the sub-problem and adjusting the model structure specifically includes: Based on the sub-problems, the current worst scenario and the historical scenario deviations, the distribution of the scenario generator is dynamically adjusted to generate new optimization constraints, and the new optimization constraints are returned to step 41 to continue iterative solution until the termination condition is met to obtain the global optimal solution.

15. A device for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error, characterized in that: Includes the following modules: Construct a power generation model module, which is used to construct power generation models of different power generation resources in the park according to wind power and photovoltaic power generation constraints, thermal power unit operation constraints, and energy storage equipment operation constraints; Construct an upper-level consumption model module to adjust the consumption of new energy based on the load demand response potential of the park, and construct an upper-level consumption model with the maximum consumption as the objective function; Construct a lower-level cost model module, which is used to construct a lower-level cost model based on the operating cost of the thermal power unit, the regulation cost of the energy storage equipment and the load regulation cost, with the minimum total cost as the objective function; The module for evaluating the new energy consumption capacity is used to evaluate the new energy consumption capacity of the park based on the power generation model, the upper-level consumption model and the lower-level cost model.

16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, it implements the method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error as described in any one of claims 1 to 14.

17. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error as described in any one of claims 1 to 14.

18. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the method for evaluating the new energy consumption capacity of a park based on power generation cost and prediction error as described in any one of claims 1 to 14.

Images