Wind power generation optimization scheduling system based on real-time wind speed

Abstract

The invention relates to the technical field of wind turbine generators, in particular to a wind power generation optimization scheduling system based on real-time wind speed. Comprising a central control unit used for establishing a plurality of equipment points according to equipment parameters of a wind power plant; the monitoring unit comprises a plurality of monitoring sub-modules, and the monitoring sub-modules are arranged at all equipment points; the monitoring sub-module is used for collecting wind speed parameters of each equipment point; the simulation unit is used for constructing an associated disturbance model according to all the equipment points; and performing prediction and optimal distribution on the power of each equipment point based on the predicted wind speed curve of each equipment point so as to set an initial control strategy of each equipment point, and when the wind speed fluctuates, performing comprehensive analysis on a plurality of optimization strategies according to a preset associated disturbance model so as to determine the optimal power of each equipment point. The overall scheduling efficiency of all wind turbine generators in the wind power plant is improved, the wake flow influence is reduced, and the overall operation income of the wind power plant is improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbines, and in particular to a wind power generation optimization scheduling system based on real-time wind speed. Background Art

[0002] Due to the intermittent and random nature of natural wind speed, wind farms experience strong power fluctuations when connected to the grid, and their impact on grid stability is becoming increasingly apparent.

[0003] One of the difficulties in wind farm power control is the randomness of wind speed. To reduce the difficulty of wind power scheduling, the mainstream control strategies in existing technologies all use wind power forecasts as the basis for power allocation, which has a significant effect on improving the effectiveness of wind farm power control strategies. However, in the above-mentioned wind turbine optimization control process, when wind speed fluctuates, adjustments are often made to a single wind turbine, ignoring the impact of wake turbulence, making it impossible to achieve optimal operating benefits of the wind farm. Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a wind power generation optimization scheduling system based on real-time wind speed, aiming to improve the optimization efficiency of wind power generation and achieve the best overall operating benefits of the wind farm.

[0005] In some embodiments of the present application, the power of each equipment point is predicted and optimally allocated based on the predicted wind speed curve of each equipment point, thereby setting the initial control strategy for each equipment point. When the wind speed fluctuates, a comprehensive analysis of multiple optimization strategies is performed according to a preset associated disturbance model, thereby improving the overall scheduling efficiency of all wind turbines in the wind farm, reducing the impact of wake turbulence, and improving the overall operating benefits of the wind farm.

[0006] In some embodiments of the present application, a wind power generation optimization scheduling system based on real-time wind speed is provided, comprising: Central control unit, used to establish multiple equipment points according to the equipment parameters of the wind farm; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are arranged at each equipment point; The monitoring submodule is used to collect wind speed parameters at each equipment point; Simulation unit, used to build a correlation disturbance model based on all equipment points; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; The second processing module is used to build a wind speed prediction model and a wind speed monitoring cycle, and generate a predicted wind speed curve for each equipment point within a single wind speed cycle; The first control module is used to set the working parameters of each equipment point according to all predicted wind speed curves and associated disturbance models; The second control module is used to set the working parameters of each monitoring submodule within a single wind speed monitoring cycle.

[0007] In some embodiments of the present application, the simulation unit includes: The first simulation module is used to construct multiple operation sub-areas according to the location parameters of all equipment points; Establish the running sub-area sequence P, P=(p1,p2…p i …p n1 ), where p i is the i-th operating sub-area; n1 is the number of operating sub-areas, and n>n1; Establish an operation sub-area-equipment point mapping table; The second simulation module is used to construct multiple wind speed fields based on historical monitoring data; Establish the wind speed field sequence W, W=(w1, w2…w i …w n2 ), where w i is the i-th wind speed field; n2 is the number of wind speed fields; The third simulation module is used to construct a correlation disturbance model based on the wind speed field sequence W and the operating sub-area sequence P.

[0008] In some embodiments of the present application, the third simulation module is further configured to: According to the wind speed field sequence W, set w in sequence i is the target wind speed field; Generate a training data package of the target wind speed field based on historical monitoring data; Generate a disturbance sub-model of the target wind speed field according to the training data package and the running sub-area sequence P; Generate disturbance sub-models of each wind speed field in sequence; Construct a correlated disturbance model based on all disturbance sub-models.

[0009] In some embodiments of the present application, the second control module is further configured to: Establish monitoring submodule sequence B, B=(b1, b2…b i …b n ), where b i is the monitoring submodule of the i-th equipment point; n is the number of equipment points; Set b in sequence according to the monitoring submodule sequence B i is the target submodule; Generate the expected fluctuation value c of the device point corresponding to the target submodule in the current monitoring period; According to the expected fluctuation value c, the pre-monitoring duration of the current wind speed cycle of the target submodule is set; Set the pre-monitoring duration of the current wind speed cycle of each monitoring submodule in turn.

[0010] In some embodiments of the present application, generating the expected fluctuation value c includes: c=e1×Q1×[ β 1i ×s i ]+e2×Q2×[ β 2i ×j i ]; Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of volatility indicators; β 1i is the influencing factor of the i-th volatility index; s i is the reference value of the i-th fluctuation index generated based on the predicted wind speed curve of the equipment point corresponding to the target submodule; θ2 is the number of equipment indicators; β 2i is the influencing factor of the i-th equipment index; j i It is the reference value of the i-th device indicator of the device point corresponding to the target submodule.

[0011] In some embodiments of the present application, the central control unit further includes: The first optimization module is used to obtain the real-time wind speed parameters of each equipment point and generate the deviation evaluation value of each equipment point based on all real-time wind speeds; The second optimization module is used to establish the deviation evaluation value F, F=(f1, f2…f i …f n ), where f i is the real-time deviation evaluation value of the i-th device point; The second optimization module is used to determine whether to generate an optimization instruction based on the deviation evaluation value sequence F.

[0012] In some embodiments of the present application, determining whether to generate an optimization instruction includes: Generate a corrected evaluation value g according to the deviation evaluation value sequence F; g=e3×Q3×[ Y(i)×(f i -f')]+e4×Q4×[ η i ×f i ]; Among them, e3 is a preset third weight coefficient; e4 is a preset fourth weight coefficient; Q3 is a preset third weight coefficient; Q4 is a preset fourth weight coefficient; f' is a preset deviation evaluation value threshold; Y(i) is a selection coefficient; if (f i -f') > 0, Y(i) = 1; if (f i -f') < 0, Y(i) = 0; η i is the influence factor of the i-th device point; preset corrected evaluation value threshold G1; If g < G1, the second optimization module generates a first-level optimization instruction.

[0013] In some embodiments of the present application, the first-level optimization instruction includes: Generating a feedback data packet according to the real-time wind speed parameters of each device point; Constructing a real-time wind speed field according to the feedback data packet, and selecting a target disturbance sub-model according to the real-time wind speed field; Generating a plurality of first-level optimization strategies according to the deviation degree evaluation value sequence F; Establishing a first-level optimization strategy sequence D, D = (d1, d2…d i …d r ), where d i is the i-th first-level optimization strategy; r is the number of first-level optimization strategies; Generating the expected revenue value of each first-level optimization strategy; Establishing an expected revenue value sequence H, H = (h1, h2…h i …h r ), where h i is the expected revenue value of the i-th first-level optimization strategy; Setting the first-level optimization strategy corresponding to the maximum value h max in the expected revenue value sequence H as the second-level optimization strategy; Correcting the working parameters of each device point according to the second-level optimization strategy.

[0014] In some embodiments of the present application, when generating the expected revenue value of each first-level optimization strategy, it includes: Sequentially setting d i as the target optimization strategy according to the first-level optimization strategy sequence D; Generating the expected revenue value h of the target optimization strategy; h = e5×Q5× η i ×k i + e6×Q6× U×η i ×t i ; Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; k i is the expected return value of the ith device point generated based on the target optimization strategy; U is the conversion coefficient; t i is the opportunity gain value lost by the i-th equipment point in the target optimization strategy generated based on the target perturbation sub-model.

[0015] Compared with the prior art, the wind power generation optimization scheduling system based on real-time wind speed in the embodiment of the present application has the following beneficial effects: Based on the predicted wind speed curve of each equipment point, the power of each equipment point is predicted and optimized, so as to set the initial control strategy of each equipment point. When the wind speed fluctuates, a comprehensive analysis of multiple optimization strategies is carried out according to the preset correlation disturbance model to improve the overall scheduling efficiency of all wind turbines in the wind farm, reduce the impact of wake, and improve the overall operating benefits of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a structural diagram of a wind power generation optimization scheduling system based on real-time wind speed in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0017] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0018] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0021] like Figure 1 As shown, a wind power generation optimization scheduling system based on real-time wind speed in a preferred embodiment of the present application includes: Central control unit, used to establish multiple equipment points according to the equipment parameters of the wind farm; The monitoring unit includes a plurality of monitoring submodules, and the monitoring submodules are arranged at each equipment point; The monitoring submodule is used to collect wind speed parameters at each equipment point; Simulation unit, used to build a correlation disturbance model based on all equipment points; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; The second processing module is used to build a wind speed prediction model and a wind speed monitoring cycle, and generate a predicted wind speed curve for each equipment point within a single wind speed cycle; The first control module is used to set the working parameters of each equipment point according to all predicted wind speed curves and associated disturbance models; The second control module is used to set the working parameters of each monitoring submodule within a single wind speed monitoring cycle.

[0022] Specifically, multiple equipment points are established according to the parameters of all wind turbines in the wind farm, and a single equipment point represents one wind turbine.

[0023] Specifically, by generating a wind speed prediction curve for each device point within a single wind speed monitoring cycle, a power prediction curve for each device point is generated, and the initial control strategy for each device point is set based on the power allocation principle.

[0024] Specifically, the monitoring unit is preferably a plurality of radar wind measuring devices, which are installed on the wind turbines at various equipment points.

[0025] Specifically, the simulation unit includes: The first simulation module is used to construct multiple operation sub-areas according to the location parameters of all equipment points; Establish the running sub-area sequence P, P=(p1,p2…p i …p n1 ), where p i is the i-th operating sub-area; n1 is the number of operating sub-areas, and n>n1; Establish an operation sub-area-equipment point mapping table; The second simulation module is used to construct multiple wind speed fields based on historical monitoring data; Establish the wind speed field sequence W, W=(w1, w2…w i …w n2 ), where w i is the i-th wind speed field; n2 is the number of wind speed fields; The third simulation module is used to construct a correlation disturbance model based on the wind speed field sequence W and the operating sub-area sequence P.

[0026] Specifically, by analyzing the historical operating parameters of the wind farm, the wake disturbance parameters and position parameters between each equipment point are generated, thereby establishing multiple operating sub-areas.

[0027] Specifically, a single operating sub-area includes multiple equipment points, and no wake disturbance is generated between the equipment points in the operating sub-area. Wake disturbance will occur between adjacent operating sub-areas.

[0028] Specifically, by analyzing the historical monitoring data in the wind farm, multiple wind speed fields are constructed. The wind direction and wind speed in each wind speed field are not exactly the same, and a single wind speed field includes the expected wind speed parameters of each equipment point.

[0029] Specifically, the third simulation module is further used to: According to the wind speed field sequence W, set w in sequence i is the target wind speed field; Generate a training data package of the target wind speed field based on historical monitoring data; Generate a disturbance sub-model of the target wind speed field according to the training data package and the running sub-area sequence P; Generate disturbance sub-models of each wind speed field in sequence; Construct a correlated disturbance model based on all disturbance sub-models.

[0030] Specifically, by analyzing the historical parameters of the target wind speed field, the wake disturbance parameters are extracted and the corresponding disturbance sub-model is constructed.

[0031] It can be understood that in the above embodiment, based on the predicted wind speed curve of each equipment point, the power of each equipment point is predicted and optimized, so as to set the initial control strategy of each equipment point. When the wind speed fluctuates, it is optimized and scheduled according to the preset associated disturbance model, thereby improving the overall operating benefits of the wind farm.

[0032] In a preferred embodiment of the present application, the second control module is further configured to: Establish monitoring submodule sequence B, B=(b1, b2…b i …b n ), where b i is the monitoring submodule of the i-th equipment point; n is the number of equipment points; Set b in sequence according to the monitoring submodule sequence B i is the target submodule; Generate the expected fluctuation value c of the device point corresponding to the target submodule in the current monitoring period; According to the expected fluctuation value c, the pre-monitoring duration of the current wind speed cycle of the target submodule is set; Set the pre-monitoring duration of the current wind speed cycle of each monitoring submodule in turn.

[0033] Specifically, the larger the expected fluctuation, the longer the corresponding forward monitoring period. This refers to the time it takes to predict sudden wind speed changes in advance using LiDAR feedforward control. The longer the forward monitoring period, the longer the corresponding scheduling adjustment period.

[0034] Specifically, when generating the expected fluctuation value c, it includes: c=e1×Q1×[ β 1i ×s i ]+e2×Q2×[ β 2i ×j i ]; Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of volatility indicators; β 1i is the influencing factor of the i-th volatility index; s i is the reference value of the i-th fluctuation index generated based on the predicted wind speed curve of the equipment point corresponding to the target submodule; θ2 is the number of equipment indicators; β 2i is the influencing factor of the i-th equipment index; j i It is the reference value of the i-th device indicator of the device point corresponding to the target submodule.

[0035] Specifically, the larger the predicted fluctuation value, the greater the possibility of wind speed fluctuation at the current equipment point, and the greater the adjustment cost of the equipment.

[0036] Specifically, all parameters in the model are normalized by presetting a first fixed coefficient and a second fixed coefficient, so that each parameter in the model is within the same value range.

[0037] Specifically, the fluctuation index includes but is not limited to the variance of the predicted wind speed curve, the discrete value, the difference between the maximum wind speed and the minimum wind speed, and other parameters.

[0038] Specifically, the equipment indicators include, but are not limited to, the operating sub-area where the equipment point is located, the fatigue of the wind turbine at the equipment point, the control cost, the historical wind speed fluctuation parameters of the equipment point, and other parameters.

[0039] Specifically, by quantifying various equipment indicators and fluctuation indicators, reference values of various equipment indicators and fluctuation indicators are generated.

[0040] In a preferred embodiment of the present application, the central control unit further includes: The first optimization module is used to obtain the real-time wind speed parameters of each equipment point and generate the deviation evaluation value of each equipment point based on all real-time wind speeds; The second optimization module is used to establish the deviation evaluation value F, F=(f1, f2…f i …f n ), where f i is the real-time deviation evaluation value of the i-th device point; The second optimization module is used to determine whether to generate an optimization instruction based on the deviation evaluation value sequence F.

[0041] Specifically, the determination of whether to generate an optimization instruction includes: Generate a corrected evaluation value g according to the deviation evaluation value sequence F; g=e3×Q3×[ Y(i)×(f i -f')]+e4×Q4×[ η i ×f i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third weight coefficient; Q4 is the preset fourth weight coefficient; f' is the preset deviation evaluation value threshold; Y(i) is the selection coefficient; if (f i -f')>0,Y(i)=1;if(f i -f')<0,Y(i)=0;η i is the impact factor of the i-th equipment point; Preset the correction evaluation value threshold G1; If g < G1, the second optimization module generates a first-level optimization instruction.

[0042] Specifically, the greater the deviation evaluation value, the greater the difference between the current wind speed fluctuation and the predicted state. It is necessary to optimize and dispatch each wind turbine in a timely manner to ensure the overall operation benefit of the wind farm.

[0043] Specifically, the influence factor of each equipment point can be set according to the importance of the equipment point. The greater the influence factor, the greater the interference fluctuation of the current equipment point on the entire wind farm system when there is an operation deviation.

[0044] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter in the model is within the same value range.

[0045] In the preferred embodiment of this application, the first-level optimization instruction includes: Generate a feedback data packet according to the real-time wind speed parameters of each equipment point; Construct a real-time wind speed field according to the feedback data packet, and select a target disturbance sub-model according to the real-time wind speed field; Generate multiple first-level optimization strategies according to the deviation degree evaluation value sequence F; Establish a first-level optimization strategy sequence D, D=(d1, d2…d i …d r ), where d i is the i-th first-level optimization strategy; r is the number of first-level optimization strategies; Generate the expected revenue value of each first-level optimization strategy; Establish an expected revenue value sequence H, H=(h1, h2…h i …h r ), where h i is the expected revenue value of the i-th first-level optimization strategy; Set the first-level optimization strategy corresponding to the maximum value h max in the expected revenue value sequence H as the second-level optimization strategy; Correct the working parameters of each equipment point according to the second-level optimization strategy.

[0046] Specifically, the greater the expected revenue value, the greater the feasibility and comprehensive revenue of the current first-level optimization strategy.

[0047] Specifically, when generating the expected revenue value of each first-level optimization strategy, it includes: Set d i as the target optimization strategy in turn according to the first-level optimization strategy sequence D; Generate the expected revenue value h of the target optimization strategy; h=e5×Q5×[ η i ×k i ]+e6×Q6×[ U×η i ×t i ]; Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; k i is the expected return value of the ith device point generated based on the target optimization strategy; U is the conversion coefficient; t i is the opportunity gain value lost by the i-th equipment point in the target optimization strategy generated based on the target perturbation sub-model.

[0048] Specifically, the sub-expected benefit value of each device point refers to the improvement in power generation efficiency and power generation at each device point after optimized scheduling. The larger the sub-expected benefit, the more efficient the current target optimization strategy is for the current device point.

[0049] Specifically, the opportunity benefit value refers to the difference between the benefit value generated by optimal scheduling of the equipment point and the sub-expected benefit value generated by scheduling based on the target optimization strategy. The larger the opportunity benefit value, the more unfavorable the target optimization strategy is for the operation of the current equipment point. By setting the conversion coefficient to process the opportunity benefit value, the larger the opportunity benefit value, the larger the corresponding expected benefit value.

[0050] Specifically, the optimal scheduling is centered on the current equipment point, and the remaining equipment points are optimized and scheduled with the goal of achieving the optimal operating state of the current equipment point.

[0051] Specifically, all parameters in the model are normalized by presetting the fifth fixed coefficient and the sixth fixed coefficient, so that each parameter in the model is within the same value range.

[0052] According to the first concept of the present application, based on the predicted wind speed curve of each equipment point, the power of each equipment point is predicted and optimally allocated, so as to set the initial control strategy of each equipment point. When the wind speed fluctuates, a comprehensive analysis of multiple optimization strategies is performed according to a preset correlation disturbance model to improve the overall scheduling efficiency of all wind turbines in the wind farm, reduce the impact of wake, and improve the overall operating benefits of the wind farm.

[0053] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A wind power generation optimization scheduling system based on real-time wind speed, characterized in that: Comprising: A central control unit for establishing multiple equipment points according to the equipment parameters of a wind farm; A monitoring unit including multiple monitoring sub-modules, and the monitoring sub-modules are arranged at each equipment point; The monitoring sub-module is used for collecting the wind speed parameters of each equipment point; A simulation unit for constructing an associated disturbance model according to all equipment points; The central control unit includes: The first processing module is used to establish a device point sequence A, A=(a1, a2…a i …a n ), where a i is the i-th device point; n is the number of device points; A second processing module for constructing a wind speed prediction model and a wind speed monitoring period, and generating a predicted wind speed curve of each equipment point within a single wind speed period; A first control module for setting the working parameters of each equipment point according to all the predicted wind speed curves and the associated disturbance model; A second control module for setting the working parameters of each monitoring sub-module within a single wind speed monitoring period.

2. The wind power generation optimization scheduling system based on real-time wind speed according to claim 1, characterized in that: The simulation unit includes: A first simulation module for constructing multiple operation sub-regions according to the position parameters of all equipment points; Establish the running sub-area sequence P, P=(p1,p2…p i …p n1 ), where p i is the i-th operating sub-area; n1 is the number of operating sub-areas, and n>n1; Establishing an operation sub-region - equipment point mapping table; A second simulation module for constructing multiple wind speed fields according to historical monitoring data; Establish the wind speed field sequence W, W=(w1, w2…w i …w n2 ), where w i is the i-th wind speed field; n2 is the number of wind speed fields; A third simulation module for constructing an associated disturbance model according to the wind speed field sequence W and the operation sub-region sequence P.

3. The wind power generation optimization scheduling system based on real-time wind speed according to claim 2, characterized in that: The third simulation module is further used for: According to the wind speed field sequence W, set w in sequence i is the target wind speed field; Generating a training data packet of the target wind speed field according to historical monitoring data; Generating a disturbance sub-model of the target wind speed field according to the training data packet and the operation sub-region sequence P; Sequentially generating the disturbance sub-models of each wind speed field; Constructing an associated disturbance model according to all the disturbance sub-models.

4. The wind power generation optimization scheduling system based on real-time wind speed according to claim 3, characterized in that: The second control module is further used for: Establish monitoring submodule sequence B, B=(b1, b2…b i …b n ), where b i is the monitoring submodule of the i-th equipment point; n is the number of equipment points; Set b in sequence according to the monitoring submodule sequence B i is the target submodule; Generating an expected fluctuation value c of the equipment point corresponding to the target sub-module within the current monitoring period; Setting the pre-monitoring duration of the current wind speed period of the target sub-module according to the expected fluctuation value c; Sequentially setting the pre-monitoring durations of the current wind speed periods of each monitoring sub-module.

5. The wind power generation optimization scheduling system based on real-time wind speed according to claim 4, characterized in that: When generating the expected fluctuation value c, it includes: c=e1×Q1×[ b 1i ×s i ]+e2×Q2×[ b 2i ×j i ]; Among them, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of volatility indicators; β 1i is the influencing factor of the i-th volatility index; s i is the reference value of the i-th fluctuation index generated based on the predicted wind speed curve of the equipment point corresponding to the target submodule; θ2 is the number of equipment indicators; β 2i is the influencing factor of the i-th equipment index; j i It is the reference value of the i-th device indicator of the device point corresponding to the target submodule.

6. The wind power generation optimization scheduling system based on real-time wind speed according to claim 4, characterized in that: The central control unit further includes: A first optimization module for obtaining the real-time wind speed parameters of each equipment point and generating a deviation evaluation value of each equipment point according to all the real-time wind speeds; The second optimization module is used to establish the deviation evaluation value F, F=(f1, f2…f i …f n ), where f i is the real-time deviation evaluation value of the i-th device point; The second optimization module is used for judging whether to generate an optimization instruction according to the deviation evaluation value sequence F.

7. The wind power generation optimization scheduling system based on real-time wind speed according to claim 6, characterized in that: When judging whether to generate an optimization instruction, it includes: Generating a correction evaluation value g according to the deviation evaluation value sequence F; g=e3×Q3×[ Y(i)×(f i -f')]+e4×Q4×[ η i ×f i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third weight coefficient; Q4 is the preset fourth weight coefficient; f' is the preset deviation evaluation value threshold; Y(i) is the selection coefficient; if (f i -f')>0,Y(i)=1;if(f i -f')<0,Y(i)=0;η i is the impact factor of the i-th equipment point; Presetting a correction evaluation value threshold G1; If g < G1, the second optimization module generates a first-level optimization instruction.

8. The wind power generation optimization scheduling system based on real-time wind speed according to claim 7, characterized in that: The first-level optimization instruction includes: Generating a feedback data packet according to the real-time wind speed parameters of each equipment point; Constructing a real-time wind speed field according to the feedback data packet, and selecting a target disturbance sub-model according to the real-time wind speed field; Generating multiple first-level optimization strategies according to the deviation degree evaluation value sequence F; Establish a first-level optimization strategy sequence D, D=(d1, d2…d i …d r ), where d i is the i-th first-level optimization strategy; r is the number of first-level optimization strategies; Generating the expected revenue value of each first-level optimization strategy; Establish the expected return value sequence H, H=(h1, h2…h i …h r ), where h i is the expected return value of the i-th level optimization strategy; Set the maximum value h in the expected return value sequence H max The corresponding first-level optimization strategy is the second-level optimization strategy; Correcting the working parameters of each equipment point according to the second-level optimization strategy.

9. The wind power generation optimization scheduling system based on real-time wind speed according to claim 8, characterized in that: When generating the expected revenue value of each first-level optimization strategy, it includes: According to the first-level optimization strategy sequence D, set d i Optimize strategies for your goals; Generating the expected revenue value h of the target optimization strategy; h=e5×Q5×[ or i ×k i ]+e6×Q6×[ U×h i ×t i ]; Among them, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; k i is the expected return value of the ith device point generated based on the target optimization strategy; U is the conversion coefficient; t i is the opportunity gain value lost by the i-th equipment point in the target optimization strategy generated based on the target perturbation sub-model.

Images