Intelligent regulation and control system for wind energy and solar energy complementary power generation under low-carbon economy

Abstract

The invention specifically relates to the technical field of energy control, and discloses a wind energy and solar energy complementary power generation intelligent regulation and control system under low-carbon economy, which comprises a data acquisition module, an energy prediction module, an energy management module, an energy storage control module, a fault diagnosis module and a man-machine interaction module, wherein the data acquisition module is used for constructing a power generation intelligent regulation and control data set; the energy prediction module is used for calculating to obtain wind energy predicted generating capacity and solar energy predicted generating capacity; the energy management module is used for formulating a dynamic power distribution strategy, the energy storage control module is used for performing energy storage control, and the fault diagnosis module is used for obtaining a fault evaluation index and judging a fault level; the man-machine interaction module is used for providing a visual interface and a strategy self-defining function; the multi-source data is dynamically displayed and integrated through the visual interface, the accuracy of intelligent regulation and control is improved, the oneness of data acquisition is broken through, the accuracy of intelligent regulation and control is improved, and the dynamic regulation and control capability of intelligent regulation and control is improved.

Description

Technical Field

[0001] The present invention relates to the field of energy control technology, and more specifically, to an intelligent control system for wind and solar energy complementary power generation in a low-carbon economy. Background Art

[0002] Global climate change and the depletion of fossil energy have driven the transformation of the energy structure towards a low-carbon one. Wind and solar energy are clean energy sources with abundant resources and wide distribution. A single energy system is difficult to meet the demand for stable power supply. By combining the complementary characteristics of wind and solar energy, the stability and efficiency of power supply can be improved, clean energy can be efficiently utilized, and the core requirements of a low-carbon economy can be met. With the development of wind power generation and photovoltaic power generation technologies, technical support has been provided for complementary power generation systems. The existing wind and solar complementary power generation intelligent control system includes power generation modules, energy storage modules, control modules, conversion modules, monitoring and communication modules, and protection and safety modules. Through multi-source collaborative optimization, intelligent control and energy storage guarantee, it can achieve efficient energy utilization and stable and reliable power supply, reduce operation and maintenance costs, and effectively improve environmental benefits.

[0003] However, in actual use, it still has some shortcomings. First, the data collection scope is limited. The sensor network of the existing wind and solar complementary power generation intelligent control system mainly focuses on basic meteorological data such as wind speed, sunlight speed and temperature, as well as equipment operation status data. It lacks the collection of carbon emission data, grid interaction data and environmental ecological data, resulting in an inability to accurately assess low-carbon benefits. Second, dynamic regulation capabilities are weak. The existing intelligent regulation system for wind and solar hybrid power generation relies on fixed threshold control, making it difficult to adapt to the complex regulation needs of a low-carbon economy. This results in insufficient real-time performance. The existing system lacks comprehensive consideration of carbon costs, grid stability, and energy storage lifespan, and is prone to data silos, resulting in insufficient dynamic regulation. Third, the synergy of multi-energy complementarity is insufficient. The existing intelligent control system for wind and solar complementary power generation does not integrate electrolyzers and fuel cell equipment. The distributed resource aggregation capability is weak, and there is a lack of access to adjustable loads, resulting in the inability to respond to demand. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides an intelligent control system for wind and solar complementary power generation under a low-carbon economy, which constructs a power generation intelligent control data set through a data acquisition module, predicts wind power generation and solar power generation through an energy prediction module, formulates a dynamic power allocation strategy through an energy management module, performs energy storage control through an energy storage control module, determines the fault level through a fault diagnosis module, and provides a strategy customization function through a human-computer interaction module, effectively solving the problems of limited data acquisition range, weak dynamic control capability, and insufficient multi-energy complementary synergy proposed in the background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent control system for wind and solar complementary power generation in a low-carbon economy, comprising a data acquisition terminal, a central control terminal, and an energy storage and grid interaction terminal, as well as a data acquisition module, an energy prediction module, an energy management module, an energy storage control module, a fault diagnosis module, and a human-computer interaction module: The data acquisition module is used to acquire power generation intelligent control data from the data acquisition terminal in real time, perform data cleaning, data standardization and multi-source heterogeneous data fusion, construct a power generation intelligent control data set, and transmit it to the energy prediction module; The energy prediction module is used to build an energy prediction model, import the power generation intelligent control data set into the energy prediction model, obtain the wind power generation forecast and solar power generation forecast, build the energy prediction data set, and pass it to the energy management module; The energy management module is used to formulate a dynamic power allocation strategy based on the power generation intelligent control data set and the energy forecast data set, build a dynamic adjustment mechanism, generate scheduling instructions, perform real-time scheduling, and pass them to the energy storage management module; The energy storage control module is used to obtain a dynamic power allocation strategy and a power generation intelligent control data set, formulate an energy storage charge and discharge control strategy based on the dynamic power allocation strategy, perform energy storage control, and perform health status management and dynamic adjustment; The fault diagnosis module is used to obtain the equipment operation data of the power generation intelligent control data set in real time, build a fault diagnosis model, obtain the fault assessment index, judge the fault level, and build a multi-level early warning mechanism to optimize the maintenance strategy and operation strategy; The human-computer interaction module is used to build a visual interactive interface, receive early warning information transmitted by the fault diagnosis module in real time, realize dynamic data visualization, perform authority management, and support relevant staff to customize control strategies.

[0006] Technical effects and advantages of the present invention: 1. The present invention collects power generation intelligent control data in real time through the data acquisition terminal and transmits it to the data acquisition module for data processing to construct a power generation intelligent control data set. It collects meteorological environment data, equipment operation data, energy storage status data, and power grid status data, breaking the singleness of data collection and dynamically displaying multi-source data through the visual interface of the human-computer interaction module, thereby improving the accuracy of intelligent control. 2. The present invention calculates a fault assessment index based on the real-time collected equipment operation data through the fault diagnosis module, determines the fault level, triggers an early warning based on the fault level, and immediately triggers an automated response based on the early warning information, achieving real-time strategic response. The human-computer interaction module also provides a strategy customization function, thereby improving the dynamic control capability of intelligent control. 3. The present invention predicts wind power generation and solar power generation through an energy prediction module, formulates a dynamic power allocation strategy based on the predicted wind power generation and solar power generation through an energy management module, and displays the relationship and real-time status of wind turbines, photovoltaic arrays and energy storage battery packs in real time through a human-computer interaction module, supports multi-source data comparison, and improves multi-energy complementary synergy through data integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0008] Figure 2 Schematic diagram of the method steps of the present invention.

[0009] Figure 3 Schematic diagram of the fault level determination steps of the present invention. DETAILED DESCRIPTION

[0010] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0011] As attached Figure 1 The intelligent control system for wind and solar complementary power generation under a low-carbon economy shown in the figure includes a data acquisition terminal, a central control terminal, and an energy storage and grid interaction terminal. It also includes a data acquisition module, an energy prediction module, an energy management module, an energy storage control module, a fault diagnosis module, and a human-computer interaction module.

[0012] In a more specific application of the present invention, the data acquisition terminal is used to obtain meteorological data, equipment operation data and power grid data in real time, providing basic data support for the intelligent regulation of wind and solar power generation. It specifically includes meteorological sensors, equipment status sensors, power grid monitoring equipment and edge computing units. The meteorological sensors can be ultrasonic anemometers, optical radiation sensors and temperature and humidity sensors. The equipment status sensors can be vibration sensors, vector measurement units and battery management systems. The power grid monitoring equipment can be power quality analyzers and phasor measurement units.

[0013] The central control terminal is used to integrate and process data. It is the core part of the system and performs data processing, algorithm calculations and decision-making control. It specifically includes the main controller, energy management system and server. The energy management system is used to run energy optimization algorithms, energy storage scheduling strategies and grid interaction control logic. The database is used to store historical operating data, weather forecast data and equipment parameters.

[0014] The energy storage grid interaction terminal is used to achieve energy storage system control, grid power regulation and power quality optimization. It specifically includes an energy storage converter, a battery cluster, an intelligent switch and a power quality conditioner. The energy storage converter supports four-quadrant operation, the battery cluster uses lithium iron phosphate batteries, and the intelligent switch is used to support rapid interruption of fault current.

[0015] The specific implementation of the present invention includes the following contents: Data acquisition module: This module acquires power generation intelligent control data from the data acquisition terminal in real time, performs data cleaning, data standardization, and multi-source heterogeneous data fusion, constructs a power generation intelligent control data set, and transmits it to the energy prediction module. Furthermore, the power generation intelligent control data includes meteorological environment data, equipment operation data, energy storage status data and grid status data; In this embodiment, it should be specifically explained that meteorological environment data specifically include wind speed, wind direction, air density, light intensity, sunshine duration, temperature, humidity and carbon emissions; equipment operation data specifically include wind turbine speed, generator voltage, photovoltaic module voltage, photovoltaic power generation power, equipment vibration frequency, power conversion efficiency and wind turbine characteristic parameters; energy storage status data specifically include battery pack voltage, battery pack current, battery pack temperature, charging power and discharging power; grid status data specifically include grid voltage, grid frequency, real-time electricity price and power load.

[0016] The acquisition of intelligent power generation control data requires real-time monitoring of wind turbines through the anemometer, wind vane and vibration sensor in the data acquisition terminal to collect wind speed, wind direction and mechanical vibration frequency, real-time monitoring of photovoltaic arrays through irradiance sensors and temperature sensors to obtain light intensity and component temperature, real-time monitoring of energy storage battery packs through the battery management system to obtain the voltage, voltage, SOC and temperature of the energy storage battery packs, and real-time monitoring of converters and inverters through voltage sensors and temperature sensors to obtain electrical parameters and equipment temperature.

[0017] Process missing values, detect and correct outliers for intelligent power generation control data, unify units, align timestamps, and standardize data types; In this embodiment, it should be specifically explained that missing value processing can adopt interpolation, deletion and filling methods, use machine learning algorithms to detect abnormal points in time series data, and combine the logic of equipment operation to judge the rationality of abnormal values. For abnormal values ​​caused by instantaneous interference, the mean before and after are used to replace them, and for abnormal values ​​caused by equipment failure, the mean before and after are used to replace them.

[0018] Multi-source heterogeneous data fusion refers to the heterogeneous data processing, spatiotemporal dimension fusion and data consistency verification of the processed power generation intelligent control data.

[0019] In this embodiment, it should be specifically explained that heterogeneous data processing refers to converting structured time series data and text data into a unified format, and defining the attribute relationship between equipment, measurement and status, so that data from different sources are mapped in a unified model. Spatiotemporal dimension fusion refers to aligning the spatiotemporal dimensions and associating the spatial dimensions of data. Data consistency verification refers to ensuring the consistency of fused data through cross-validation, and performing data traceability and correction.

[0020] Energy prediction module: Builds an energy prediction model, imports the power generation intelligent control data set into the energy prediction model, obtains the predicted wind power generation and solar power generation, builds the energy prediction data set, and transmits it to the energy management module; Furthermore, the calculation of wind power generation forecast requires obtaining the average value of data in the intelligent power generation control data set within a day, including air density ρ, wind speed v, wind direction-wind turbine angle θ, equipment vibration frequency f, power conversion efficiency η and swept area S. The equipment vibration frequency and power conversion efficiency are calculated using the formula Calculate the fan efficiency η w , where η w0 Indicates the fan efficiency under standard working conditions, f b Indicates the vibration frequency threshold, and the swept area and wind direction-fan angle are calculated using the formula Calculate the effective swept area S e , the air density, wind speed, fan efficiency and effective swept area are introduced into the energy prediction model, and the formula is used Calculate the predicted wind energy generation E within the prediction time t w .

[0021] In this embodiment, it should be specifically explained that the data average value refers to the average value of the power generation intelligent control data within a day based on the current time, which can effectively represent the comprehensive situation of the power generation intelligent control data within a day. The wind direction-wind turbine angle represents the angle between the wind direction and the wind turbine. The change in the angle affects the efficiency of converting wind energy into electrical energy. The vibration frequency and electrical energy conversion efficiency in the above process refer to the vibration frequency and electrical energy conversion efficiency of the wind turbine.

[0022] Furthermore, the calculation of solar power generation forecast requires obtaining the average value of data in the intelligent power generation control data set within a day, including light intensity L, photovoltaic module area S1, temperature T, equipment vibration frequency f, power conversion efficiency η, comprehensive correction coefficient K and carbon emissions C. The temperature, equipment vibration frequency and power conversion efficiency are used in the formula Calculate the photovoltaic module efficiency η s , where η s0 represents the efficiency of photovoltaic modules under standard working conditions, a represents the temperature coefficient, f bIndicates the vibration frequency threshold, and the comprehensive correction coefficient K and carbon emissions C are used using the formula Calculate the effective comprehensive correction coefficient K e , C b Indicates the carbon emission threshold, and imports the light intensity, photovoltaic module area, photovoltaic module efficiency and effective comprehensive correction coefficient into the energy prediction model, using the formula Calculate the predicted solar energy power generation E within the prediction time t s , where t e Indicates the effective illumination duration within the prediction duration.

[0023] In this embodiment, it should be specifically explained that the above-mentioned equipment vibration frequency and electric energy conversion efficiency refer to the equipment vibration frequency and electric energy conversion efficiency of photovoltaic modules. The acquisition of the comprehensive correction coefficient requires historical power generation intelligent control data, data preprocessing of the historical power generation intelligent control data, and correlation analysis and principal component analysis are performed on the historical power generation intelligent control data. A comprehensive correction coefficient model is constructed, a mapping relationship between the correction coefficient and the influencing factor is established, the obtained comprehensive correction coefficient is calculated and verified, and the comprehensive correction coefficient is updated regularly.

[0024] Energy Management Module: Develops dynamic power allocation strategies based on the power generation intelligent control dataset and energy forecast dataset, builds a dynamic adjustment mechanism, generates scheduling instructions, performs real-time scheduling, and transmits them to the energy storage management module. Furthermore, the formulation of a dynamic power allocation strategy requires obtaining the historical average power load in the intelligent power generation control data set and the wind power forecast and solar power forecast in the energy forecast data set within the forecast period, and comparing the wind power forecast and solar power forecast with the power load to construct a power allocation priority, including the first priority, the second priority, and the third priority. The power allocation priority is determined based on the comparison results, and the corresponding power allocation strategy is adopted based on the power allocation priority within the forecast period.

[0025] In this embodiment, it should be specifically explained that the historical average power load refers to the average value of power loads of multiple prediction periods of equal length t before the current moment.

[0026] The first priority in the power allocation priority means that when the predicted wind power generation and solar power generation within the forecast period is greater than the power load, the corresponding power allocation strategy is to directly use wind and solar power for power supply, and store the remaining power in the energy storage battery group; the second priority means that when the predicted wind power generation and solar power generation within the forecast period is greater than the power load and the SOC of the energy storage battery group is <90%, the energy storage battery group is charged, and when the predicted wind power generation and solar power generation within the forecast period is less than the power load and the SOC of the energy storage battery group is >20%, the energy storage battery is used to provide the unmet power load; the third priority means that when the predicted wind power generation and solar power generation within the forecast period is less than the power load and the SOC of the energy storage battery group is <20%, the grid is used to supply power to provide the unmet power load.

[0027] Furthermore, the construction of a dynamic adjustment mechanism requires real-time correction based on the forecast errors of wind power generation and solar power generation, adaptive adjustment of equipment status based on equipment operating status data in the intelligent power generation control data set, and the formulation of extreme weather emergency strategies.

[0028] In this embodiment, it should be specifically explained that real-time correction through prediction error specifically refers to comparing the predicted wind power generation and solar power generation within every 15 minutes with the actual power generation value. When the deviation value exceeds 10%, the power allocation is recalculated. When the actual power generation value is greater than the predicted value, the charging power of the energy storage battery group is increased. When the actual power generation value is less than the predicted value, the discharging power of the energy storage battery group is increased.

[0029] Energy storage control module: This module obtains dynamic power allocation strategies and intelligent power generation control data sets, formulates energy storage charging and discharging control strategies based on the dynamic power allocation strategies, performs energy storage control, and performs health status management and dynamic adjustments. Furthermore, the formulation of energy storage charge and discharge control strategies requires obtaining the dispatch instructions corresponding to the dynamic power allocation strategy and the equipment operation data and energy storage status data in the power generation intelligent control data set. Based on the real-time data obtained, the energy storage battery charge and discharge requirements are determined, and the corresponding charge and discharge strategies are formulated according to the charge and discharge requirements. In this embodiment, it should be specifically noted that formulating corresponding charge-discharge strategies according to charge-discharge requirements specifically means that when the energy storage battery pack needs to be charged, it preferentially absorbs the excess power generated by wind and solar power generation, but does not exceed the maximum charging power of the energy storage battery pack, and performs segmented charging according to the SOC state. When SOC < 20%, constant current charging is adopted; when 20% < SOC < 80%, constant power charging is adopted; when SOC > 80%, constant voltage charging is adopted. When the energy storage battery pack needs to be discharged, it needs to supplement the deficit power of the power consumption load, but does not exceed the maximum discharge power of the energy storage battery pack, and preferentially provides power to important places.

[0030] Control the energy storage battery pack to charge and discharge according to the charge-discharge strategy; During the energy storage control process, perform state of charge management, battery balancing and thermal management, and perform prediction error correction and extreme weather adaptation.

[0031] In this embodiment, it should be specifically noted that state of charge management needs to adjust the charge-discharge depth according to the battery health state of the energy storage battery pack and correct the error of current measurement. Battery balancing means adjusting the voltage of single cells through a hardware balancing circuit to avoid overcharging and over-discharging of single cells. Extreme weather adaptation means that when the energy storage battery is in a high-temperature environment, the charging power of the energy storage battery pack needs to be limited to less than 80% of the rated value to avoid battery overheating. When the energy storage battery pack is in a low-temperature environment, the battery needs to be preheated before charging to improve the charge-discharge efficiency.

[0032] Fault diagnosis module: Real-time obtain the device operation data of the power generation intelligent regulation data set, construct a fault diagnosis model, obtain a fault evaluation index, judge the fault level, and construct a multi-level early warning mechanism to optimize the maintenance strategy and operation strategy; Furthermore, calculating the fault evaluation index requires setting a time window and obtaining the average value of the device operation data within this time window, specifically including the fan speed v w , the fan voltage V w , the photovoltaic module voltage V s , the photovoltaic power generation power P, the device vibration frequency f, and the power conversion efficiency η. Import them into the fault diagnosis model, perform standardization processing on the data, and obtain the normal threshold interval of each device operation parameter , where μ represents the parameter mean, σ represents the parameter standard deviation, and k represents the parameter confidence level. When the device operation parameter is within the normal threshold interval, I i = 0. When the device operation parameter exceeds the normal threshold interval, , X i represents the i-th parameter in the device operation parameter, I irepresents the fault contribution value corresponding to the i-th parameter, b represents the amplification factor, and the formula is used The fault assessment index is calculated, and c represents the scale factor.

[0033] In this embodiment, it should be specifically explained that the purpose of standardizing the equipment operating parameters is to convert parameters of different dimensions into dimensionless values ​​in the interval [0,1] to avoid errors caused by dimensionality problems. The acquisition of the amplification coefficient and scale factor requires obtaining historical equipment operation data, which should include normal data and fault data, and marking the degree of abnormality of each parameter. The calculation results of the above formula containing the amplification coefficient and scale factor are matched with the actual fault impact, and the values ​​of the amplification coefficient and scale factor are obtained based on the actual impact.

[0034] Furthermore, the fault levels include the first fault level, the second fault level, the third fault level and the fourth fault level. The fault level is determined based on the fault assessment index, and a corresponding early warning mechanism is constructed based on the fault level. A maintenance strategy is generated based on the historical fault assessment index, and the fault risk is reduced by adjusting the equipment operating parameters.

[0035] In this embodiment, it should be specifically explained that the judgment of the fault level means that when the fault assessment index is less than 1, it indicates that the device is in the first fault level, indicating that the device is in normal operation; when the fault assessment index is greater than 1 and less than 3, it indicates that the device is in the second fault level, indicating that the device is in a warning state, there is a slight abnormality, and attention needs to be paid to the operation of the device; when the fault assessment index is greater than 3 and less than 5, it indicates that the device is in the third fault level, indicating that the device is in a fault state, there is an abnormality in the operation of the device, and maintenance is required; when the fault assessment index is greater than 5, it indicates that the device is in the fourth fault level, indicating that the device is in a serious fault state, there is a risk of failure of the device, and emergency shutdown is required.

[0036] Specifically, the early warning mechanism means that when the device is at the second fault level, a first-level warning will be issued, with pop-up prompts, abnormal data will be recorded and continuously monitored. When the device is at the third fault level, a second-level warning will be issued, and the operation and maintenance personnel will be notified via SMS and email, and a preliminary fault location report will be generated. When the device is at the fourth fault level, a third-level warning will be issued, the backup equipment will be automatically activated, the device will be forced to shut down and an audible and visual alarm will be issued.

[0037] Human-computer interaction module: Build a visual interactive interface, receive early warning information transmitted by the fault diagnosis module in real time, realize dynamic data visualization, perform authority management, and support relevant staff to customize control strategies.

[0038] Furthermore, the visual interactive interface includes an overview dashboard, an equipment status monitoring area, a data analysis and prediction area, and an operation control area. User roles include system administrators, operation and maintenance engineers, data analysts, and ordinary users, and user role permissions are divided.

[0039] In this embodiment, it should be specifically explained that the overview dashboard is used to present core system indicators, such as real-time wind power generation and solar power generation, energy storage battery group SOC, power load and the number of fault warnings. The equipment status monitoring area uses the form of an equipment topology diagram to display the real-time status of the wind turbine, photovoltaic array and energy storage battery group, and uses red to indicate equipment failure. The data analysis and prediction area uses data charts to display historical power generation trends and fault frequency distribution. The operation control area uses buttons and command sending portals to provide manual operation functions.

[0040] like Figure 2 As shown, the present invention provides an intelligent control method for wind and solar energy complementary power generation, and the specific steps are as follows: S1: The data acquisition terminal collects power generation intelligent control data in real time and transmits it to the data acquisition module for data cleaning, data standardization, and multi-source heterogeneous data fusion to construct a power generation intelligent control data set; S2: Build an energy forecast model through the energy forecast module, import the power generation intelligent control data set into the energy forecast model, obtain the predicted wind power generation and solar power generation, and build the energy forecast data set; S3: The energy management module formulates a dynamic power allocation strategy based on the power generation intelligent control data set and the energy forecast data set, builds a dynamic adjustment mechanism, generates scheduling instructions based on the allocation strategy, and performs real-time scheduling; S4: The energy storage control module obtains the dynamic power allocation strategy and power generation intelligent control data set, formulates the energy storage charging and discharging control strategy based on the allocation strategy, performs energy storage control, and performs health status management and dynamic adjustment. S5: The fault diagnosis module acquires equipment operation data in real time, builds a fault diagnosis model, obtains a fault assessment index, determines the fault level, and builds a multi-level early warning mechanism to optimize maintenance and operation strategies. S6: Build a visual interactive interface through the human-computer interaction module, receive early warning information from the fault diagnosis module in real time, realize dynamic data visualization, perform authority management, and support relevant staff to customize control strategies.

[0041] like Figure 3 As shown, the present invention provides a method for determining the fault level, and the specific steps are as follows: A1: When the fault assessment index is less than 1, it means that the equipment is in the first fault level, indicating that the equipment is in normal operation; A2: When the fault assessment index is greater than 1 and less than 3, it indicates that the device is in the second fault level, indicating that the device is in a warning state; A3: When the fault assessment index is greater than 3 and less than 5, it means that the device is in the third fault level, indicating that the device is in a fault state; A4: When the fault assessment index is greater than 5, it means that the device is in the fourth fault level, indicating that the device is in a serious fault state.

[0042] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict. Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The intelligent control system for wind and solar complementary power generation under the low-carbon economy is characterized by: It includes data acquisition terminal, central control terminal and energy storage grid interaction terminal, as well as data acquisition module, energy prediction module, energy management module, energy storage control module, fault diagnosis module and human-computer interaction module: The data acquisition module is used to acquire power generation intelligent control data from the data acquisition terminal in real time, perform data cleaning, data standardization and multi-source heterogeneous data fusion, construct a power generation intelligent control data set, and transmit it to the energy prediction module; The energy prediction module is used to build an energy prediction model, import the power generation intelligent control data set into the energy prediction model, obtain the wind power generation forecast and solar power generation forecast, build the energy prediction data set, and pass it to the energy management module; The energy management module is used to formulate a dynamic power allocation strategy based on the power generation intelligent control data set and the energy forecast data set, build a dynamic adjustment mechanism, generate scheduling instructions, perform real-time scheduling, and pass them to the energy storage management module; The energy storage control module is used to obtain a dynamic power allocation strategy and a power generation intelligent control data set, formulate an energy storage charge and discharge control strategy based on the dynamic power allocation strategy, perform energy storage control, and perform health status management and dynamic adjustment; The fault diagnosis module is used to obtain the equipment operation data of the power generation intelligent control data set in real time, build a fault diagnosis model, obtain the fault assessment index, judge the fault level, and build a multi-level early warning mechanism to optimize the maintenance strategy and operation strategy; The human-computer interaction module is used to build a visual interactive interface, receive early warning information transmitted by the fault diagnosis module in real time, realize dynamic data visualization, perform authority management, and support relevant staff to customize control strategies.

2. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The power generation intelligent control data includes meteorological environment data, equipment operation data, energy storage status data and power grid status data; Process missing values, detect and correct outliers for intelligent power generation control data, unify units, align timestamps, and standardize data types; Multi-source heterogeneous data fusion refers to the heterogeneous data processing, spatiotemporal dimension fusion and data consistency verification of the processed power generation intelligent control data.

3. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The calculation of wind power generation prediction requires obtaining the average value of data in the power generation intelligent control data set within one day, including air density ρ, wind speed v, wind direction-wind turbine angle θ, equipment vibration frequency f, power conversion efficiency η and swept area S, and the equipment vibration frequency and power conversion efficiency are calculated using the formula Calculate the fan efficiency η w , where η w0 Indicates the fan efficiency under standard working conditions, f b Indicates the vibration frequency threshold, and the swept area and wind direction-fan angle are calculated using the formula Calculate the effective swept area S e , the air density, wind speed, fan efficiency and effective swept area are introduced into the energy prediction model, and the formula is used Calculate the predicted wind energy generation E within the prediction time t w .

4. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The calculation of the predicted solar power generation requires obtaining the average value of the data in the intelligent power generation control data set within one day, including light intensity L, photovoltaic module area S1, temperature T, equipment vibration frequency f, power conversion efficiency η, comprehensive correction coefficient K and carbon emissions C. The temperature, equipment vibration frequency and power conversion efficiency are used in the formula Calculate the photovoltaic module efficiency η s , where η s0 represents the efficiency of photovoltaic modules under standard working conditions, a represents the temperature coefficient, f b Indicates the vibration frequency threshold, and the comprehensive correction coefficient K and carbon emissions C are used using the formula Calculate the effective comprehensive correction coefficient K e , C b Indicates the carbon emission threshold, and imports the light intensity, photovoltaic module area, photovoltaic module efficiency and effective comprehensive correction coefficient into the energy prediction model, using the formula Calculate the predicted solar energy power generation E within the prediction time t s , where t e Indicates the effective illumination duration within the prediction duration.

5. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The formulation of the dynamic power allocation strategy requires obtaining the historical average power load in the intelligent power generation control data set and the wind power generation forecast and solar power generation forecast in the energy forecast data set within the forecast period, and comparing the wind power generation and solar power generation with the power load, constructing the power allocation priority, including the first priority, the second priority and the third priority, judging the power allocation priority based on the comparison result, and adopting the corresponding power allocation strategy based on the power allocation priority within the forecast period.

6. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The construction of the dynamic adjustment mechanism requires real-time correction based on the prediction errors of wind power generation and solar power generation, adaptive adjustment of equipment status based on equipment operating status data in the power generation intelligent control data set, and formulation of extreme weather emergency strategies.

7. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The formulation of the energy storage charging and discharging control strategy requires obtaining the scheduling instructions corresponding to the dynamic power allocation strategy and the equipment operation data and energy storage status data in the power generation intelligent control data set, judging the energy storage battery charging and discharging needs based on the real-time data obtained, and formulating the corresponding charging and discharging strategy based on the charging and discharging needs.

8. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The calculation of the fault assessment index requires setting a time window and obtaining the average value of the equipment operation data within the time window, specifically including the fan speed v w , fan voltage V w , PV module voltage V s , photovoltaic power generation power P, equipment vibration frequency f and power conversion efficiency η, which are imported into the fault diagnosis model, and the data are standardized to obtain the normal threshold range of each equipment operating parameter , where μ represents the parameter mean, σ represents the parameter standard deviation, and k represents the parameter confidence. When the equipment operating parameters are within the normal threshold range, I i =0, when the equipment operating parameters exceed the normal threshold range, , X i Indicates the i-th parameter in the equipment operating parameters, I i represents the fault contribution value corresponding to the i-th parameter, b represents the amplification factor, and the formula is used The fault assessment index is calculated, and c represents the scale factor.

9. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The fault levels include the first fault level, the second fault level, the third fault level and the fourth fault level. The fault level is determined based on the fault assessment index, and a corresponding early warning mechanism is constructed based on the fault level. A maintenance strategy is generated based on the historical fault assessment index, and the fault risk is reduced by adjusting the equipment operating parameters.

10. The intelligent control system for wind and solar complementary power generation in a low-carbon economy according to claim 1 is characterized by: The visual interactive interface includes an overview dashboard, an equipment status monitoring area, a data analysis and prediction area, and an operation control area. User roles include system administrators, operation and maintenance engineers, data analysts, and ordinary users, and user role permissions are divided.

Images