Operation scheduling method and system for wind-photovoltaic combined power generation system, and device and medium

Abstract

The present invention relates to the technical field of power systems, and specifically relates to an operation scheduling method and system for a wind-photovoltaic combined power generation system, and a device and a medium. The method comprises the following steps: using a Gaussian mixture model to model prediction errors of wind power and photovoltaic outputs, and on the basis of the prediction errors, obtaining a predicted output of a system; using system efficiency maximization, system power fluctuation minimization, carbon emission reduction maximization and the lowest energy-curtailment penalty as optimization objective functions of the system; determining constraint conditions of the optimization objective functions; and on the basis of the constraint conditions and the predicted output, using an NSGA-II algorithm to perform solving, and on the basis of a solving result, determining a scheduling plan for the wind-photovoltaic combined power generation system within a preset time period. The present invention can effectively improve the economic benefits of the system, greatly reduces the grid connection fluctuation, also significantly improves the carbon emission reduction capability of the wind-photovoltaic combined system, and has higher feasibility.

Description

Operation scheduling method, system, device and medium of wind-solar hybrid power generation system TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, in particular to an operation scheduling method, system, device and medium of a wind-solar hybrid power generation system. BACKGROUND

[0002] With the rapid development of wind power and photovoltaic power generation technology, large-scale wind power and photovoltaic power generation grid-connected operation will inevitably become a development trend. Unlike traditional thermal power and hydropower, the output power of the two depends on meteorological conditions, so it is completely uncontrollable, random, volatile and intermittent. Direct grid connection will cause problems such as reduced power generation income of power stations, large grid-connected power fluctuation, more wind and light abandoned power, and reduced carbon emission reduction, so it is necessary to study the power system scheduling method of wind and light power stations. At present, the scheduling scheme of wind and light power stations coordinates and optimizes the operation of these resources, and simultaneously adjusts the output of new energy to match, which is complex and may easily lead to low efficiency.

[0003] SUMMARY

[0004] The present application relates to the technical field of power systems, in particular to an operation scheduling method, system, device and medium of a wind-solar hybrid power generation system.

[0005] Embodiments of the present application are implemented by the following technical solutions: an operation scheduling method of a wind-solar hybrid power generation system, comprising the following steps:

[0006] The prediction error of wind power and photovoltaic output is modeled using a Gaussian mixture model, and the predicted output of the system is obtained based on the prediction error;

[0007] The system benefit maximization, system power fluctuation minimization, carbon emission reduction maximization, and energy abandonment penalty minimization are used as the optimization objective function of the system;

[0008] The constraint conditions of the optimization objective function are determined;

[0009] Based on the constraint conditions and the predicted output, the NSGA-II algorithm is used for solving, and according to the solving result, the scheduling plan of the wind-solar hybrid power generation system in a preset time period is determined, and the operation of the wind-solar hybrid power generation system is scheduled according to the scheduling plan.

[0010] According to a preferred embodiment, the sum of the determined wind power and photovoltaic power prediction value and the prediction error is used to represent the predicted output of the system, and the expression is as follows:

[0011] In the above formula, denotes the wind power prediction output at time t, and M denotes the number of wind farm units in operation, denotes the wind power prediction value of the i-th unit, denotes the wind power prediction error of the i-th unit, denotes the photovoltaic prediction output, and N denotes the number of photovoltaic power station units in operation, denotes the photovoltaic power prediction value of the j-th unit, denotes the photovoltaic power prediction error of the j-th unit.

[0012] According to a preferred embodiment, the calculation expression of the is as follows:

[0013] In the above formula, v i,t denotes the actual wind speed at the corresponding position of the i-th unit at time t, denotes the cut-in wind speed at the corresponding position of the i-th unit at time t, v r denotes the rated wind speed, denotes the rated output power of the i-th unit, denotes the cut-out wind speed at the corresponding position of the i-th unit at time t.

[0014] According to a preferred embodiment, the calculation expression of the is as follows:

[0015] In the above formula, denotes the actual light radiation density at the corresponding position of the j-th unit at time t, denotes the area of the photovoltaic cell panel of the i-th unit, denotes the photoelectric conversion efficiency of the photovoltaic cell panel of the j-th unit, H STC denotes the standard light radiation density.

[0016] According to a preferred embodiment, the probability density function expression of the Gaussian mixture model is as follows:

[0017] In the above formula, n denotes the number of sub-Gaussian distributions of the Gaussian mixture model in the interval, a k denotes the weighting coefficient, and f(x|θ k denotes the probability density function of the k-th sub-Gaussian distribution contained;

[0018] The expression of f(x|θ k is as follows:

[0019] In the above formula, σ kdenotes the variance of the kth sub-Gaussian distribution, x denotes any sample value of the sample set of wind power and photovoltaic power prediction error within the interval, and μ k denotes the mean value of the kth sub-Gaussian distribution.

[0020] According to a preferred embodiment, the optimization objective function expression of the system is as follows:

[0021] In the above formula, N denotes the number of intra-day scheduling periods, Pri t denotes the on-grid price at time t, denotes the wind curtailment in scheduling calculation at time t, denotes the light curtailment in scheduling calculation at time t, denotes the carbon quota sales price at time t, V t denotes the carbon quota at time t, E t denotes the carbon emission at time t, P avg denotes the average output of the wind-solar hybrid power generation system, CS wind denotes the coal consumption of wind power generation converted into thermal power generation, CS pv denotes the coal consumption of photovoltaic power generation converted into thermal power generation, denotes the carbon emission generated by unit coal consumption of thermal power generation, denotes the wind curtailment penalty factor at time t, denotes the light curtailment penalty factor at time t.

[0022] According to a preferred embodiment, the constraint condition includes that the on-grid power of wind power and photovoltaic power is less than or equal to the maximum predicted output, and the expression is as follows:

[0023] In the above formula, denotes the maximum predicted output of wind power at time t, denotes the maximum predicted output of photovoltaic power at time t.

[0024] The application also provides a wind-solar hybrid power generation system operation scheduling system, comprising:

[0025] a prediction module configured to model the prediction error of wind power and photovoltaic output by using a Gaussian mixture model, and obtain the predicted output of the system based on the prediction error;

[0026] a construction module configured to take the minimum total operation cost of the system, the minimum system power fluctuation, the maximum carbon emission reduction, and the minimum energy curtailment penalty as the optimization objective function of the system;

[0027] a setting module configured to determine the constraint condition of the optimization objective function;

[0028] The solution module is used to solve the problem based on the constraints and predicted output using the NSGA-II algorithm, determine the scheduling plan of the wind power and photovoltaic combined power generation system within a preset time period based on the solution results, and schedule the operation of the wind power and photovoltaic combined power generation system according to the scheduling plan.

[0029] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described above.

[0030] The present invention also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method described above.

[0031] The technical solutions for the operation and scheduling method, system, equipment and medium of the wind-solar combined power generation system of the present invention have at least the following advantages and beneficial effects: the present invention can effectively improve the economic benefits of the system, greatly reduce grid connection fluctuations, and significantly improve the carbon emission reduction capacity of the wind-solar combined system, and has high feasibility. Attached Figure Description

[0032] Figure 1 is a flowchart illustrating the operation and scheduling method of the wind-solar combined power generation system provided in Embodiment 1 of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0034] Example 1

[0035] Referring to Figure 1, this embodiment of the invention provides an operation and scheduling method for a combined wind and solar power generation system; more specifically, the method includes the following steps:

[0036] In wind and solar power forecasting, forecast uncertainty mainly stems from forecast errors, and the distribution characteristics of these errors are crucial for developing more reliable power system dispatch plans. Studies show that forecast errors follow a normal distribution and account for approximately 10% of the predicted output. Therefore, using a Gaussian Mixture Model (GMM) to model the forecast errors of wind power output can help estimate the probability density distribution of these errors more accurately, thereby improving the accuracy of wind power output forecasting. Therefore, in step one of this embodiment, a Gaussian Mixture Model is used to model the forecast errors of wind and solar power output, and the predicted output of the system is obtained based on these forecast errors.

[0037] More specifically, in this embodiment of the invention, the predicted output of the system is characterized by the sum of the determined predicted wind power and photovoltaic power values ​​and the prediction error, as expressed below:

[0038] In the above formula, This represents the predicted wind power output at time t, and M represents the number of wind farm units in operation. This represents the predicted wind power output of the i-th turbine unit. This represents the wind power prediction error for the i-th turbine unit. This represents the predicted output of photovoltaic power plants, where N represents the number of photovoltaic power plant units in operation. This represents the predicted photovoltaic power of the j-th unit. This represents the prediction error of the photovoltaic power of the j-th unit.

[0039] Among them, the The calculation expression is as follows:

[0040] In the above formula, v i,t This represents the actual wind speed at the location of the i-th generator unit at time t. v represents the cut-in wind speed at the location corresponding to the i-th unit at time t. r Indicates the rated wind speed. This represents the rated output power of the i-th unit. Let represent the cut-out wind speed at the corresponding position of the i-th unit at time t.

[0041] The The calculation expression is as follows:

[0042] In the above formula, This represents the actual solar radiation density at the location corresponding to the j-th generating unit at time t. This represents the area of ​​the photovoltaic panels in the i-th generating unit. H represents the photoelectric conversion efficiency of the photovoltaic panel of the j-th unit. STC This represents the standard light radiation density.

[0043] Regarding the Gaussian mixture model, it should be noted that its probability density function expression is as follows:

[0044] In the above formula, n represents the number of sub-Gaussian distributions of the Gaussian mixture model in that interval, and a k Denotes the weighting coefficients, f(x|θ) k ) represents the probability density function of the k-th sub-Gaussian distribution;

[0045] f(x|θ k The expression for ) is as follows:

[0046] In the above formula, σ k Let μ represent the variance of the k-th sub-Gaussian distribution, x represent any sample value of the wind power and photovoltaic power prediction error sample set within this interval, and μ represent the variance of the k-th sub-Gaussian distribution. k Let represent the mean of the k-th sub-Gaussian distribution.

[0047] Step 2: The optimization objective function of the system is to maximize system benefits, minimize system power fluctuations, maximize carbon emission reductions, and minimize energy curtailment penalties.

[0048] More specifically, the expression for maximizing system benefits is as follows:

[0049] The expression for minimizing system power fluctuations is as follows:

[0050] The expression for maximizing carbon emission reduction is as follows:

[0051] The expression with the lowest energy forfeiture penalty is as follows:

[0052] In the above formula, N represents the number of scheduling periods within a day, and Pri t This represents the on-grid electricity price at time t. This represents the wind curtailment power calculated during time t. This represents the power of light wasted in the scheduling calculation at time t. V represents the carbon quota price at time t. t E represents the carbon quota at time t. t P represents the carbon emissions at time t. avg CS represents the average output of the combined wind and solar power system. wind This represents the coal consumption of wind power generation converted to thermal power generation, CS. pv This represents the coal consumption for photovoltaic power generation converted to thermal power generation. This indicates the carbon emissions generated per unit of coal consumed in thermal power generation. This represents the wind curtailment penalty factor at time t. Let t represent the light-discarding penalty factor at time t.

[0053] Step 3: Determine the constraints of the optimization objective function.

[0054] More specifically, the constraints include that the grid-connected power of wind power and photovoltaic power is less than or equal to the maximum predicted output, as expressed below:

[0055] In the above formula, This represents the maximum predicted wind power output at time t. This represents the maximum predicted photovoltaic output at time t.

[0056] Step 4: Based on the constraints and predicted output, the NSGA-II algorithm is used to solve the problem. Based on the solution results, the scheduling plan for the wind power and photovoltaic combined power generation system within the preset time period is determined, and the operation of the wind power and photovoltaic combined power generation system is scheduled according to the scheduling plan.

[0057] It should be noted that the NSGA-II algorithm's implementation process includes the following key steps: First, an initial population containing multiple individuals is randomly generated, each representing a potential solution; then, the individuals in the population are sorted using a non-dominated sorting technique, stratified according to the level of non-dominated solutions among them; next, a crowding comparison operator is used to handle individuals at the same non-dominated level to ensure the diversity of the solution set; finally, an elitist strategy is used to retain a portion of the optimal solutions for the next generation of the population. This algorithm effectively balances the quality and diversity of the solution set, resulting in a uniform distribution of the obtained Pareto optimal solutions, exhibiting good convergence and robustness. Furthermore, compared with other genetic algorithms, NSGA-II significantly improves the algorithm's running speed while ensuring the quality of the solutions.

[0058] In summary, this invention can effectively improve the economic benefits of the system, greatly reduce grid connection volatility, and significantly improve the carbon emission reduction capacity of the wind-solar combined system, thus demonstrating high feasibility.

[0059] Example 2

[0060] This invention provides an operation and scheduling system for a wind-solar combined power generation system, comprising: a prediction module for modeling the prediction errors of wind and solar power output using a Gaussian mixture model, and obtaining the predicted output of the system based on the prediction errors; a construction module for setting the system's optimization objective function as minimizing total system operating cost, minimizing system power fluctuation, maximizing carbon emission reduction, and minimizing curtailment penalty; a setting module for determining the constraints of the optimization objective function; and a solution module for solving the system using the NSGA-II algorithm based on the constraints and the predicted output, determining a scheduling plan for the wind-solar combined power generation system within a preset time period based on the solution results, and scheduling the operation of the wind-solar combined power generation system according to the scheduling plan.

[0061] Example 3

[0062] This invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in Embodiment 1.

[0063] Example 4

[0064] This invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in Embodiment 1.

[0065] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for operation scheduling of a wind-solar hybrid power generation system, characterized in that, The method comprises the following steps: modeling prediction errors of wind power and photovoltaic power output by using a Gaussian mixture model, and obtaining predicted output of the system based on the prediction errors; taking system benefit maximization, system power fluctuation minimization, carbon emission reduction maximization, and minimum energy abandonment penalty as an optimization objective function of the system; determining constraint conditions of the optimization objective function; based on the constraint conditions and the predicted output, solving by using an NSGA-II algorithm, and determining a dispatching plan of the wind-photovoltaic combined power generation system in a preset time period according to a solving result, and dispatching operation of the wind-photovoltaic combined power generation system according to the dispatching plan.

2. The operation scheduling method of the wind-solar hybrid power generation system according to claim 1, characterized in that, The predicted output of the system is characterized by a certain wind power and photovoltaic power prediction value and the sum of the prediction errors, expressed as follows: In the above formulae, P(t) represents the wind power prediction output at time t, M represents the number of wind farm units in operation, represents the predicted value of the wind power of the i-th unit, denotes the prediction error of the i-th wind turbine, denotes the photovoltaic predicted output, N denotes the photovoltaic power plant unit operation number, denotes the jth unit A set of photovoltaic power prediction values, denotes the jth unit photovoltaic power prediction error.

3. The operation scheduling method of the wind-solar hybrid power generation system according to claim 2, wherein The The computational expression for the following: In the above formula, v i,t represents the actual wind speed at the position corresponding to the i th unit at time t, vi(t) represents the cut-in wind speed of the i-th unit at time t, r vR represents the rated wind speed, Pn,i represents the rated output power of the i-th unit, denotes the cut-out wind speed of the ith unit at the tth time.

4. The operation scheduling method of the wind-solar hybrid power generation system according to claim 2, wherein The The computational expression for the In the above formulae, represents the actual light radiation density of the jth unit at the corresponding position at time t, S represents the area of the i-th set of photovoltaic panels, Hj represents the photoelectric conversion efficiency of the jth set of photovoltaic panels, H STC H represents the standard light radiation density.

5. The operation scheduling method of the wind-solar hybrid power generation system according to any one of claims 3 to 4, characterized in that, The probability density function expression of the Gaussian mixture model is as follows: In the above formula, n represents the number of sub-Gaussian distributions of the Gaussian mixture model of the interval, a k represents a weighting coefficient, f(x|θ k ) represents a probability density function of the kth sub-Gaussian distribution included f(x | 0 k The expression for f(x | 0 In the above formula, σ k denotes the variance of the kth sub-Gaussian distribution, x denotes an arbitrary sample value of the wind power and photovoltaic power prediction error sample set within the interval, μ k denotes the mean of the kth sub-Gaussian distribution.

6. The operation scheduling method of the wind-solar hybrid power generation system according to claim 5, wherein The optimization objective function expression of the system is as follows: In the above formula, N represents the number of intra-day scheduling periods, Pri t represents the online electricity price at time t, represents the curtailed wind power in the dispatching calculation at time t, represents the rejected light power in the dispatching calculation at time t, denotes the carbon quota price at time t, V t denotes the carbon quota at time t, E t denotes the carbon emission at time t, P avg denotes the average output of the combined wind and solar power system, CS wind denotes the coal consumption of wind power converted into thermal power, CS pv denotes the coal consumption of photovoltaic power converted into thermal power, carbon emission amount generated by a unit coal consumption of thermal power generation, represents the wind curtailment penalty factor at time t, denotes the ith unit at the tth time. abandoned light penalty factor.

7. The operation scheduling method of the wind-solar hybrid power generation system according to claim 6, characterized in that, The constraint condition includes that the on-grid power of wind power and photovoltaic is less than or equal to the maximum predicted output, expressed as follows: In the above formulae, represents the maximum predicted output of the wind power at time t, denotes the maximum predicted output of the photovoltaic power at the tth time.

8. An operation scheduling system of a wind-solar hybrid power generation system, characterized by, The method comprises the following steps: a prediction module, configured to model prediction errors of wind power and photovoltaic power output by using a Gaussian mixture model, and obtain predicted output of the system based on the prediction errors; a construction module, configured to take system total operation cost minimization, system power fluctuation minimization, carbon emission reduction maximization, and minimum energy abandonment penalty as an optimization objective function of the system; a setting module, configured to determine constraint conditions of the optimization objective function; a solving module, configured to, based on the constraint conditions and the predicted output, solve by using an NSGA-II algorithm, and determine a dispatching plan of the wind-photovoltaic combined power generation system in a preset time period according to a solving result, and dispatch operation of the wind-photovoltaic combined power generation system according to the dispatching plan.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and is executed by the processor to implement the method of any one of claims 1 to 7.

Images