Wind power energy hybrid scale regulation and control method and system based on data analysis

Abstract

The invention relates to the technical field of wind power dispatching, and discloses a wind power energy hybrid scale regulation and control method and system based on data analysis. According to the method, historical wind speed data in a wind power plant are collected and processed, and a wind speed probability model and a wind power model are constructed based on the obtained processed historical wind speed data; meanwhile, historical electric energy data in the power network are collected, the collected historical electric energy data are processed based on a power grid constraint method, and a power grid constraint objective function is obtained; acquiring the current energy price and energy loss in real time, constructing an energy cost objective function based on the obtained wind speed probability model and the wind power model, and acquiring the electric energy demand quantity of the power network in real time; the minimum cost meeting the electric energy demand of the power network is calculated through the particle swarm optimization and the constructed energy cost objective function, and finally the calculated minimum cost is verified and regulated, so that the cost of wind power energy hybrid scale regulation is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power dispatching, and in particular to a wind power energy hybrid scale control method and system based on data analysis. Background Art

[0002] With the further advancement of sustainable development goals, wind power energy mix scale regulation methods have become a research focus. However, due to uncertainties such as the randomness and intermittency of renewable energy such as wind energy in the power generation process, the dynamic cost of wind power energy mix scale regulation is uncontrollable.

[0003] The existing Chinese patent application CN117559548A, the invention establishes a wind power prediction model and multiple wind power areas; establishes a wind power prediction model to predict the long-term power of the wind power area and constructs a curve series, and obtains the real-time operating parameters of the wind power area according to the preset control time node, and generates control instructions according to the real-time operating parameters of the wind power area. At the same time, based on the established wind power prediction model and the expected power supply demand curve of the power grid, multiple initial power generation allocation plans are generated, and the optimal screening is performed to generate a first-level power generation plan. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a method and system for wind power energy hybrid scale control based on data analysis, which has the advantages of accuracy, high efficiency, real-time and low cost, and solves the problem of uncontrollable dynamic cost of wind power energy hybrid scale control.

[0006] (II) Technical solution

[0007] In order to solve the above-mentioned technical problem of uncontrollable dynamic cost of wind power energy hybrid scale regulation, the present invention provides the following technical solutions:

[0008] The present invention discloses a wind power energy hybrid scale control method based on data analysis, which specifically includes the following steps:

[0009] S1. Collecting historical wind speed data in the wind farm, and processing the collected historical wind speed data in the wind farm based on a data processing method to obtain processed historical wind speed data;

[0010] S2. constructing a wind speed probability model and a wind power model based on the processed historical wind speed data;

[0011] S3, collecting historical electric energy data in the power network, processing the collected historical electric energy data based on the power grid constraint method, and obtaining the power grid constraint objective function;

[0012] S4. Collect the current energy price and energy loss in real time, and build an energy cost objective function based on the obtained wind speed probability model and wind power model;

[0013] S5. Collect the power demand of the power network in real time, and calculate the minimum cost of meeting the power demand of the power network through the particle swarm algorithm and the constructed energy cost objective function;

[0014] S6. Issue control instructions based on the calculated minimum cost of meeting the power demand of the power network to control the power data of the power network.

[0015] The present invention is adopted.

[0016] Preferably, the collecting of historical wind speed data in the wind farm and processing the collected historical wind speed data in the wind farm based on a data processing method to obtain the processed historical wind speed data comprises the following steps:

[0017] The data standardization processing formula is as follows:

[0018]

[0019] Where X represents the historical wind speed data before standardization. Represents the historical wind speed data after standardization; X max Indicates the maximum wind speed in the historical wind speed data, X min Indicates the minimum wind speed in historical wind speed data.

[0020] The present invention collects historical wind speed data in a wind farm for processing, and constructs a wind speed probability model and a wind power model based on the processed historical wind speed data; at the same time, collects historical electric energy data in the power network, processes the collected historical electric energy data based on a power grid constraint method, and obtains a power grid constraint objective function; then, collects the current energy price and energy loss in real time, and constructs an energy cost objective function based on the obtained wind speed probability model and the wind power model; at the same time, collects the electric energy demand of the power network in real time, calculates the minimum cost that meets the electric energy demand of the power network through a particle swarm algorithm and the constructed energy cost objective function, and finally verifies the calculated minimum cost and performs regulation, thereby reducing the cost of wind power energy hybrid scale regulation.

[0021] Preferably, constructing a wind speed probability model and a wind power model based on the processed historical wind speed data comprises the following steps:

[0022] S21, constructing a wind power model based on the processed historical wind speed data;

[0023] S22. Construct a wind speed probability model based on the processed historical wind speed data.

[0024] Preferably, constructing a wind power model based on the processed historical wind speed data comprises the following steps:

[0025] The wind power model is as follows:

[0026]

[0027] Among them, v in The cut-in wind speed of the wind turbine indicates the lower limit of wind speed for the wind turbine to generate electricity, v out is the cut-out wind speed of the wind turbine, indicating the upper limit of the wind speed for the wind turbine to generate electricity, v is the actual wind speed, P E Indicates the rated power of the fan, P w (v) represents the wind power output based on the current wind speed, v N Indicates the set rated wind speed of the fan.

[0028] Preferably, constructing a wind speed probability model based on the processed historical wind speed data comprises the following steps:

[0029] The wind speed probability model is as follows:

[0030]

[0031] Among them, f(v) represents the wind speed probability, e represents the natural logarithm, α represents the mean of the historical wind speed data, and β represents the standard deviation of the historical wind speed data.

[0032] The present invention collects historical wind speed data in a wind farm, and standardizes the collected historical wind speed data in the wind farm based on a data processing method to obtain standardized historical wind speed data in the wind farm, thereby ensuring the accuracy of the historical wind speed data in the wind farm.

[0033] Preferably, the collecting of historical electric energy data in the power network, processing the collected historical electric energy data based on the power grid constraint method, and obtaining the power grid constraint objective function comprises the following steps:

[0034] The grid constraints are as follows:

[0035]

[0036] Among them, P Gallow Indicates the total power generated by the long-term operation of the grid motor, P Lallow Indicates the maximum power allowed for long-term operation of the power grid line, P i represents the total power generated by the i-th motor in the grid, P Gi represents the active power of the i-th motor in the power grid, i∈(1,...,m), m represents the number of motors in the power grid, Pj represents the actual power demand of the jth line of the power grid, P Lj represents the active power of the jth line load in the power grid, j∈(1,...,n), n represents the number of power grid lines, and Δ represents the power grid constraint variable;

[0037] When the grid constraint variable Δ is greater than 0, it indicates that the power network is abnormal. When the grid constraint variable Δ is less than or equal to 0, it indicates that the power network is operating normally.

[0038] The present invention constructs a wind speed probability model and a wind power model based on the processed historical wind speed data, establishes a connection between wind speed and output wind power and determines the probability of wind speed, realizes the prediction of wind speed, and improves the controllability of wind power energy hybrid scale regulation.

[0039] Preferably, the real-time collection of current energy prices and energy losses, and the construction of an energy cost objective function based on the obtained wind speed probability model and wind power model include the following steps:

[0040] The conversion loss of wind energy to electric energy is set to be constant;

[0041] The energy cost objective function is as follows:

[0042] C 总 =min(∑C 电 +C 风 );

[0043] C 电 = real-time energy price × energy loss;

[0044] C 风 = wind speed probability × wind power output at current wind speed × conversion loss;

[0045] Among them, C 总 represents the total cost, C 电 represents the total power cost of each motor in the grid, C 风 Represents the cost of output wind power.

[0046] The present invention collects current energy prices and energy losses in real time, constructs an energy cost objective function based on the obtained wind speed probability model and wind power model, establishes a connection between wind power energy mix scale regulation and energy cost, and improves the controllability of the dynamic cost of wind power energy mix scale regulation.

[0047] Preferably, the real-time collection of the electric energy demand of the power network and the calculation of the minimum cost of meeting the electric energy demand of the power network by using a particle swarm algorithm and a constructed energy cost objective function include the following steps:

[0048] S51, collecting the power demand of the power network in real time and the wind power output of the total power generated by each motor in the power grid + wind speed;

[0049] Each particle is set to represent the wind power output of a group of power grid motors with total power generated + wind speed output;

[0050] S52, particle swarm optimization algorithm parameter initialization;

[0051] Set the group size and the maximum number of iterations d max , particle random position q, particle velocity u and inertia factor

[0052] S53, calculating the fitness of each particle;

[0053] The fitness calculation formula for each particle is as follows:

[0054]

[0055] Among them, Fit represents the particle fitness;

[0056] S54, updating of the best position of a single particle;

[0057] The update formula for a single particle velocity is as follows:

[0058]

[0059] Among them, u y (d+1) represents the velocity of particle y in the d+1th iteration, u y (d) represents the velocity of particle y in the dth iteration process, represents the inertia factor, q y (d) represents the position of particle y in the dth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], and k y represents the individual extreme value of particle y, k g Represents the global extreme value of all particles;

[0060] The formula for updating the position of a single particle is as follows:

[0061] q y (d+1)=u y (d+1)+q y (d);

[0062] Among them, q y (d+1) represents the position of particle y during the d+1th iteration;

[0063] For each particle calculated, the fitness of its current position is compared with the best position q it has passed.best If the fitness of the current position is greater than the best position q it has passed, best The fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ;

[0064] S55, updating of the optimal position of the group;

[0065] For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ;

[0066] S56, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

[0067] The inertia factor update formula is as follows:

[0068]

[0069] in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, d represents the current number of iterations, and d max Indicates the maximum number of iterations;

[0070] S57, repeating steps S53-S56 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position;

[0071] The inertia factor corresponding to the optimal output position is set to the minimum cost of meeting the power network's power demand.

[0072] The present invention collects the electric energy demand of the power network in real time, calculates the minimum cost to meet the electric energy demand of the power network based on the particle swarm algorithm and the constructed energy cost objective function, calculates the cost of wind power output by the total power and wind speed generated by each motor in each group of power grids by constructing a fitness function, and calculates the minimum cost to meet the electric energy demand of the power network by an iterative optimization method, thereby improving the efficiency of dynamic cost control.

[0073] Preferably, the issuing of control instructions based on the calculated minimum cost of satisfying the power demand of the power network and regulating the power data of the power network comprises the following steps:

[0074] The total power generated by each motor in the power grid corresponding to the minimum cost calculated to meet the power network's power demand is input into the power grid constraint objective function to determine whether there is an abnormality in the power network;

[0075] When the total power generated by each motor in the corresponding power grid in the minimum cost of meeting the power network's power demand results in an abnormality in the power network, the currently calculated minimum cost of meeting the power network's power demand is discarded, and step S5 is re-executed to recalculate the minimum cost of meeting the power network's power demand;

[0076] On the contrary, control instructions are issued based on the calculated minimum cost to meet the power demand of the power network to regulate the power data of the power network.

[0077] The present invention ensures the accuracy of wind power energy hybrid scale regulation by inputting the total power generated by each motor in the power grid corresponding to the minimum cost of meeting the power network power demand into the power grid constraint objective function through secondary verification.

[0078] The present invention also discloses a wind power energy hybrid scale control system based on data analysis, comprising: a data acquisition module, a data processing module, a wind power model construction module, a power grid constraint objective function construction module, a cost analysis module and a control verification module;

[0079] The data acquisition module is used to collect various parameter data in the wind farm, and transmit the collected various parameter data to the data processing module and the power grid constraint objective function module;

[0080] The data processing module is used to process the received parameter data and transmit the processed data to the wind power model building module;

[0081] The wind power model building module is used to build a wind power model according to the processed wind speed data and predict the output wind power;

[0082] The power grid constraint objective function construction module is used to process the received parameter data to obtain the power grid constraint objective function;

[0083] The cost analysis module is used to perform cost analysis based on the particle swarm algorithm and various parameters collected in real time, and output the minimum cost;

[0084] The control verification module is used to verify the minimum cost of the output.

[0085] (III) Beneficial effects

[0086] Compared with the prior art, the present invention provides a wind power energy hybrid scale control method and system based on data analysis, which has the following beneficial effects:

[0087] 1. The invention collects historical wind speed data in the wind farm for processing, and constructs a wind speed probability model and a wind power model based on the processed historical wind speed data; at the same time, it collects historical electric energy data in the power network, processes the collected historical electric energy data based on the power grid constraint method, and obtains the power grid constraint objective function; then, by real-time collection of current energy prices and energy losses, and constructing an energy cost objective function based on the obtained wind speed probability model and wind power model, at the same time, by real-time collection of the power demand of the power network, the minimum cost to meet the power demand of the power network is calculated through the particle swarm algorithm and the constructed energy cost objective function, and finally the calculated minimum cost is verified and regulated, thereby reducing the cost of wind power energy hybrid scale regulation.

[0088] 2. The invention collects historical wind speed data in the wind farm, and standardizes the collected historical wind speed data in the wind farm based on a data processing method to obtain standardized historical wind speed data in the wind farm, thereby ensuring the accuracy of the historical wind speed data in the wind farm.

[0089] 3. The invention constructs a wind speed probability model and a wind power model based on the processed historical wind speed data, establishes the connection between wind speed and output wind power and determines the probability of wind speed, realizes the prediction of wind speed, and improves the controllability of wind power energy mix scale regulation.

[0090] 4. The invention collects historical electric energy data in the power network and processes the collected historical electric energy data based on the power grid constraint method, establishes a power grid constraint objective function according to the load of each motor in the power grid and the power generated, and monitors the power network with the established power grid constraint objective function, thereby improving the safety of the power network.

[0091] 5. This invention collects current energy prices and energy losses in real time, constructs an energy cost objective function based on the obtained wind speed probability model and wind power model, establishes the connection between wind power energy mix scale regulation and energy cost, and improves the controllability of the dynamic cost of wind power energy mix scale regulation.

[0092] 6. The invention collects the power demand of the power network in real time, calculates the minimum cost to meet the power demand of the power network based on the particle swarm algorithm and the constructed energy cost objective function, calculates the cost of wind power generated by the total power and wind speed output of each motor in each group of power grid by constructing a fitness function, and calculates the minimum cost to meet the power demand of the power network by iterative optimization, thereby improving the efficiency of dynamic cost control.

[0093] 7. The invention ensures the accuracy of wind power energy mix scale regulation by inputting the total power generated by each motor in the grid corresponding to the minimum cost of meeting the power network's electricity demand into the grid constraint objective function through secondary verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 It is a schematic diagram of the wind power energy hybrid scale control process structure of the present invention. DETAILED DESCRIPTION

[0095] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0096] Example 1

[0097] See also Figure 1 This embodiment discloses a wind power energy hybrid scale control method based on data analysis, which specifically includes the following steps:

[0098] S1. Collecting historical wind speed data in the wind farm, and processing the collected historical wind speed data in the wind farm based on a data processing method to obtain processed historical wind speed data;

[0099] Collecting historical wind speed data in a wind farm, and processing the collected historical wind speed data in the wind farm based on a data processing method to obtain the processed historical wind speed data includes the following steps:

[0100] The data standardization processing formula is as follows:

[0101]

[0102] Where X represents the historical wind speed data before standardization. Represents the historical wind speed data after standardization; X max Indicates the maximum wind speed in the historical wind speed data, X min Indicates the minimum wind speed in the historical wind speed data;

[0103] S2. constructing a wind speed probability model and a wind power model based on the processed historical wind speed data;

[0104] Building a wind speed probability model and a wind power model based on the processed historical wind speed data includes the following steps:

[0105] S21, constructing a wind power model based on the processed historical wind speed data;

[0106] The wind power model is as follows:

[0107]

[0108] Among them, v in The cut-in wind speed of the wind turbine indicates the lower limit of wind speed for the wind turbine to generate electricity, v out is the cut-out wind speed of the wind turbine, indicating the upper limit of the wind speed for the wind turbine to generate electricity, v is the actual wind speed, P E Indicates the rated power of the fan, P w (v) represents the wind power output based on the current wind speed, v N Indicates the set rated wind speed of the fan;

[0109] S22, constructing a wind speed probability model based on the processed historical wind speed data;

[0110] The wind speed probability model is as follows:

[0111]

[0112] Among them, f(v) represents the wind speed probability, e represents the natural logarithm, α represents the mean of historical wind speed data, and β represents the standard deviation of historical wind speed data;

[0113] S3, collecting historical electric energy data in the power network, processing the collected historical electric energy data based on the power grid constraint method, and obtaining the power grid constraint objective function;

[0114] Collecting historical power data in the power network, processing the collected historical power data based on the power grid constraint method, and obtaining the power grid constraint objective function includes the following steps:

[0115] The grid constraints are as follows:

[0116]

[0117] Among them, P Gallow Indicates the total power generated by the long-term operation of the grid motor, P Lallow Indicates the maximum power allowed for long-term operation of the power grid line, P irepresents the total power generated by the i-th motor in the grid, P Gi represents the active power of the i-th motor in the power grid, i∈(1,...,m), m represents the number of motors in the power grid, P j represents the actual power demand of the jth line of the power grid, P Lj represents the active power of the jth line load in the power grid, j∈(1,...,n), n represents the number of power grid lines, and Δ represents the power grid constraint variable;

[0118] Furthermore, when the grid constraint variable Δ is greater than 0, it indicates that the power network is abnormal, and when the grid constraint variable Δ is less than or equal to 0, it indicates that the power network is operating normally;

[0119] S4. Collect the current energy price and energy loss in real time, and build an energy cost objective function based on the obtained wind speed probability model and wind power model;

[0120] Real-time collection of current energy prices and energy losses, and construction of energy cost objective function based on the obtained wind speed probability model and wind power model include the following steps:

[0121] The conversion loss of wind energy to electric energy is set to be constant;

[0122] The energy cost objective function is as follows:

[0123] C 总 =min(∑C 电 +C 风 );

[0124] C 电 = real-time energy price × energy loss;

[0125] C 风 = wind speed probability × wind power output at current wind speed × conversion loss;

[0126] Among them, C 总 represents the total cost, C 电 represents the total power cost of each motor in the grid, C 风 represents the cost of the output wind power;

[0127] S5. Collect the power demand of the power network in real time, and calculate the minimum cost of meeting the power demand of the power network through the particle swarm algorithm and the constructed energy cost objective function;

[0128] The power demand of the power network is collected in real time, and the minimum cost of meeting the power demand of the power network is calculated by the particle swarm algorithm and the constructed energy cost objective function, which includes the following steps:

[0129] S51, collecting the power demand of the power network in real time and the wind power output of the total power generated by each motor in the power grid + wind speed;

[0130] Each particle is set to represent the wind power output of a group of power grid motors with total power generated + wind speed output;

[0131] S52, particle swarm optimization algorithm parameter initialization;

[0132] Set the group size and the maximum number of iterations d max , particle random position q, particle velocity u and inertia factor

[0133] S53, calculating the fitness of each particle;

[0134] The fitness calculation formula for each particle is as follows:

[0135]

[0136] Among them, Fit represents the particle fitness;

[0137] S54, updating of the best position of a single particle;

[0138] The update formula for a single particle velocity is as follows:

[0139]

[0140] Among them, u y (d+1) represents the velocity of particle y in the d+1th iteration, u y (d) represents the velocity of particle y in the dth iteration process, represents the inertia factor, q y (d) represents the position of particle y in the dth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], and k y represents the individual extreme value of particle y, k g Represents the global extreme value of all particles;

[0141] The formula for updating the position of a single particle is as follows:

[0142] q y (d+1)=u y (d+1)+q y (d);

[0143] Among them, q y (d+1) represents the position of particle y during the d+1th iteration;

[0144] For each particle calculated, the fitness of its current position is compared with the best position q it has passed.best If the fitness of the current position is greater than the best position q it has passed, best The fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ;

[0145] S55, updating of the optimal position of the group;

[0146] For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ;

[0147] S56, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

[0148] The inertia factor update formula is as follows:

[0149]

[0150] in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, d represents the current number of iterations, and d max Indicates the maximum number of iterations;

[0151] S57, repeating steps S53-S56 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position;

[0152] The inertia factor corresponding to the optimal output position is set to the minimum cost of meeting the power demand of the power network;

[0153] S6, issuing control instructions based on the calculated minimum cost of meeting the power demand of the power network, and regulating the power data of the power network;

[0154] The regulation instruction is issued based on the calculated minimum cost of meeting the power demand of the power network, and the regulation of the power data of the power network includes the following steps:

[0155] The total power generated by each motor in the power grid corresponding to the minimum cost calculated to meet the power network's power demand is input into the power grid constraint objective function to determine whether there is an abnormality in the power network;

[0156] When the total power generated by each motor in the corresponding power grid in the minimum cost of meeting the power network's power demand results in an abnormality in the power network, the currently calculated minimum cost of meeting the power network's power demand is discarded, and step S5 is re-executed to recalculate the minimum cost of meeting the power network's power demand;

[0157] On the contrary, based on the calculated minimum cost to meet the power demand of the power network, control instructions are issued to control the power data of the power network;

[0158] Example 2

[0159] This embodiment also discloses a wind power energy hybrid scale control system based on data analysis, including: a data acquisition module, a data processing module, a wind power model construction module, a power grid constraint objective function construction module, a cost analysis module and a control verification module;

[0160] The data acquisition module is used to collect various parameter data in the wind farm, and transmit the collected various parameter data to the data processing module and the power grid constraint objective function module;

[0161] The data processing module is used to process the received parameter data and transmit the processed data to the wind power model building module;

[0162] The wind power model building module is used to build a wind power model according to the processed wind speed data and predict the output wind power;

[0163] The power grid constraint objective function construction module is used to process the received parameter data to obtain the power grid constraint objective function;

[0164] The cost analysis module is used to perform cost analysis based on the particle swarm algorithm and various parameters collected in real time, and output the minimum cost;

[0165] The control verification module is used to verify the minimum cost of the output;

[0166] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A wind power energy hybrid scale control method based on data analysis, characterized in that: The following steps are involved: S1. Collecting historical wind speed data in the wind farm, and processing the collected historical wind speed data in the wind farm based on a data processing method to obtain processed historical wind speed data; S2. constructing a wind speed probability model and a wind power model based on the processed historical wind speed data; S3, collecting historical electric energy data in the power network, processing the collected historical electric energy data based on the power grid constraint method, and obtaining the power grid constraint objective function; S4. Collect the current energy price and energy loss in real time, and build an energy cost objective function based on the obtained wind speed probability model and wind power model; S5. Collect the power demand of the power network in real time, and calculate the minimum cost of meeting the power demand of the power network through the particle swarm algorithm and the constructed energy cost objective function; S6. Issue control instructions based on the calculated minimum cost of meeting the power demand of the power network to control the power data of the power network.

2. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The collecting of historical wind speed data in the wind farm and processing the collected historical wind speed data in the wind farm based on the data processing method to obtain the processed historical wind speed data includes the following steps: The data standardization processing formula is as follows: Where X represents the historical wind speed data before standardization. Represents the historical wind speed data after standardization; X max Indicates the maximum wind speed in the historical wind speed data, X min Indicates the minimum wind speed in historical wind speed data.

3. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The construction of a wind speed probability model and a wind power model based on the processed historical wind speed data comprises the following steps: S21, constructing a wind power model based on the processed historical wind speed data; S22. Construct a wind speed probability model based on the processed historical wind speed data.

4. The method for controlling wind power energy mix scale based on data analysis according to claim 3 is characterized in that: The step of constructing a wind power model based on the processed historical wind speed data comprises the following steps: The wind power model is as follows: Among them, v in The cut-in wind speed of the wind turbine indicates the lower limit of wind speed for the wind turbine to generate electricity, v out is the cut-out wind speed of the wind turbine, indicating the upper limit of the wind speed for the wind turbine to generate electricity, v is the actual wind speed, P E Indicates the rated power of the fan, P w (v) represents the wind power output based on the current wind speed, v N Indicates the set rated wind speed of the fan.

5. The method for controlling wind power energy mix scale based on data analysis according to claim 3 is characterized in that: The process of constructing a wind speed probability model based on the processed historical wind speed data comprises the following steps: The wind speed probability model is as follows: Among them, f(v) represents the wind speed probability, e represents the natural logarithm, α represents the mean of the historical wind speed data, and β represents the standard deviation of the historical wind speed data.

6. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The collecting of historical electric energy data in the power network, processing the collected historical electric energy data based on the power grid constraint method, and obtaining the power grid constraint objective function comprises the following steps: The grid constraints are as follows: Among them, P Gallow Indicates the total power generated by the long-term operation of the grid motor, P Lallow Indicates the maximum power allowed for long-term operation of the power grid line, P i represents the total power generated by the i-th motor in the grid, P Gi represents the active power of the i-th motor in the power grid, i∈(1,...,m), m represents the number of motors in the power grid, P j represents the actual power demand of the jth line of the power grid, P Lj represents the active power of the jth line load in the power grid, j∈(1,...,n), n represents the number of power grid lines, and Δ represents the power grid constraint variable; When the grid constraint variable Δ is greater than 0, it indicates that the power network is abnormal. When the grid constraint variable Δ is less than or equal to 0, it indicates that the power network is operating normally.

7. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The real-time collection of current energy prices and energy losses and the construction of an energy cost objective function based on the obtained wind speed probability model and wind power model include the following steps: The conversion loss of wind energy to electric energy is set to be constant; The energy cost objective function is as follows: C 总 =min(∑C 电 +C 风 ); C 电 = real-time energy price × energy loss; C 风 = wind speed probability × wind power output at current wind speed × conversion loss; Among them, C 总 represents the total cost, C 电 represents the total power cost of each motor in the grid, C 风 Represents the cost of exported wind power.

8. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The real-time collection of the electric energy demand of the power network and the calculation of the minimum cost of meeting the electric energy demand of the power network by using the particle swarm algorithm and the constructed energy cost objective function include the following steps: S51, collecting the power demand of the power network in real time and the wind power output of the total power generated by each motor in the power grid + wind speed; Each particle is set to represent the wind power output of a group of power grid motors with total power generated + wind speed output; S52, particle swarm optimization algorithm parameter initialization; Set the group size and the maximum number of iterations d max , particle random position q, particle velocity u and inertia factor S53, calculating the fitness of each particle; The fitness calculation formula for each particle is as follows: Among them, Fit represents the particle fitness; S54, updating of the best position of a single particle; The formula for updating the velocity of a single particle is as follows: Among them, u y (d+1) represents the velocity of particle y in the d+1th iteration, u y (d) represents the velocity of particle y in the dth iteration process, represents the inertia factor, q y (d) represents the position of particle y in the dth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], and k y represents the individual extreme value of particle y, k g Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: q y (d+1)=u y (d+1)+q y (d); Among them, q y (d+1) represents the position of particle y during the d+1th iteration; For each particle calculated, the fitness of its current position is compared with the best position q it has passed. best If the fitness of the current position is greater than the best position q it has passed, best The fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ; S55, updating of the optimal position of the group; For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ; S56, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; The inertia factor update formula is as follows: in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, d represents the current number of iterations, and d max Indicates the maximum number of iterations; S57, repeating steps S53-S56 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position; The inertia factor corresponding to the optimal output position is set to the minimum cost of meeting the power network's power demand.

9. The method for controlling wind power energy mix scale based on data analysis according to claim 1 is characterized in that: The step of issuing a control instruction based on the calculated minimum cost of satisfying the power demand of the power network and regulating the power data of the power network comprises the following steps: The total power generated by each motor in the power grid corresponding to the minimum cost calculated to meet the power network's power demand is input into the power grid constraint objective function to determine whether there is an abnormality in the power network; When the total power generated by each motor in the corresponding power grid in the minimum cost of meeting the power network's power demand results in an abnormality in the power network, the currently calculated minimum cost of meeting the power network's power demand is discarded, and step S5 is re-executed to recalculate the minimum cost of meeting the power network's power demand; On the contrary, control instructions are issued based on the calculated minimum cost to meet the power demand of the power network to regulate the power data of the power network.

10. A system for implementing the wind power energy hybrid scale control method based on data analysis as described in any one of claims 1 to 9, characterized in that: include: Data acquisition module, data processing module, wind power model building module, power grid constraint objective function building module, cost analysis module and control verification module; The data acquisition module is used to collect various parameter data in the wind farm, and transmit the collected various parameter data to the data processing module and the power grid constraint objective function module; The data processing module is used to process the received parameter data and transmit the processed data to the wind power model building module; The wind power model building module is used to build a wind power model according to the processed wind speed data and predict the output wind power; The power grid constraint objective function construction module is used to process the received parameter data to obtain the power grid constraint objective function; The cost analysis module is used to perform cost analysis based on the particle swarm algorithm and various parameters collected in real time, and output the minimum cost; The control verification module is used to verify the minimum cost of the output.

Images