Multi-protocol fused water-wind-light cooperative control and remote diagnosis method and related equipment

Abstract

The invention provides a multi-protocol fused water-wind-light cooperative control and remote diagnosis method and related equipment, and is applied to the technical field of data processing. According to the invention, a whole-process technical system of data acquisition, early warning, diagnosis, control, management and evaluation is constructed around cooperative control and remote diagnosis of a water-wind-light power generation system. The method comprises the following steps: firstly, collecting operation data and multi-source environment parameters of core equipment, monitoring states of key parts through edge calculation, and generating preliminary fault early warning and power abnormity prompts; a simulation platform is built by means of digital twinning, and a diagnosis instruction and a power distribution scheme are generated in combination with a multi-objective optimization algorithm; then, a self-adaptive cooperative control algorithm is used for linkage with a power grid load and meteorological data to adjust output, and a cooperative control strategy is formed; and finally, the information of the whole link is integrated, comprehensive evaluation information including reliability, benefits and the like of the system is output, and accurate fault diagnosis and efficient operation of the system are realized.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and related equipment for integrated multi-protocol water-wind-solar collaborative control and remote diagnostics. Background Technology

[0002] With the rapid development of the renewable energy industry, hydro-wind-solar hybrid power generation systems have become an important direction for energy structure transformation due to their ability to integrate the output characteristics of different energy sources and improve power supply stability. However, these systems are characterized by diverse equipment types (photovoltaic modules, wind turbines, hydro turbines, energy storage devices, etc.), dispersed deployment areas, and heterogeneous communication protocols (such as Modbus, IEC61850, MQTT, etc.), leading to increasingly prominent core technology bottlenecks, as detailed below: The core equipment of hydro-wind-solar power generation systems comes from different manufacturers and uses significantly different communication protocols. The lack of a unified data acquisition and fusion mechanism makes it difficult to achieve efficient communication of operational data from various devices (such as photovoltaic module output, wind turbine speed, and hydro turbine flow rate) and multi-source environmental parameters (such as irradiance, wind speed, and grid load). Furthermore, existing monitoring methods often focus on the localized state of individual devices, failing to provide coordinated monitoring of critical components across devices and regions (such as photovoltaic inverters, wind turbine gearboxes, and energy storage batteries), making it difficult to identify potential fault risks in advance.

[0003] The system's operating conditions are significantly affected by weather conditions and grid load fluctuations, and the fault modes are complex and interconnected. Traditional fault diagnosis methods rely on manual experience or single threshold judgments, lacking dynamic simulation and source analysis of fault conditions, resulting in low diagnostic accuracy and delayed response. Furthermore, fault handling and power dispatch are disconnected, making it difficult to quickly adjust the output ratio of each power generation unit when equipment fails, which can easily lead to power supply instability or energy waste.

[0004] Due to the dispersed deployment of systems, existing remote management solutions lack unified communication standards and resource scheduling mechanisms. This results in poor compatibility of cross-regional control command transmission, unreasonable allocation of operation and maintenance resources, and difficulty in achieving global collaborative operation and maintenance. Furthermore, control strategies are mostly based on fixed rules, failing to dynamically adapt to changes in grid load and weather forecasts, making it difficult to balance the three core objectives of fault diagnosis accuracy, power supply stability, and power generation efficiency.

[0005] Existing assessment methods often focus on single indicators (such as power generation efficiency and failure rate), lacking a comprehensive assessment model that covers multiple dimensions such as the effectiveness of fault handling, the rationality of resource allocation, and energy-saving benefits. This makes it impossible to fully reflect the system's operating status and provide a scientific basis for subsequent optimization and upgrading.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0008] According to one aspect of this application, a method for integrated multi-protocol hydro-wind-solar coordinated control and remote diagnosis is provided, comprising: acquiring operating data of core equipment and multi-source environmental parameter information of a hydro-wind-solar power generation system; processing the operating data and multi-source environmental parameter information of the core equipment of the hydro-wind-solar power generation system, and combining edge computing nodes to monitor the efficiency of photovoltaic inverters, wear status of wind turbine gearboxes, sealing performance of water turbines, and SOC / SOH of energy storage batteries in real time, generating preliminary fault warning information and power output anomaly prompts; processing the preliminary fault warning information and power output anomaly prompts, building a virtual simulation platform for hydro-wind-solar coordinated operation through digital twin technology, simulating the system output characteristics under different fault conditions, designing hierarchical diagnosis strategies and coordinated scheduling plans by combining multi-objective optimization algorithms, and applying grid security measures. Based on full constraints and equipment operating threshold limits, target fault diagnosis commands and power coordination allocation schemes are generated. These commands and schemes are then processed using corresponding adaptive cooperative control algorithms. Real-time grid load demand and weather forecasts are combined to dynamically adjust the output ratio of each power generation unit, generating a cooperative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency. This cooperative control strategy is then processed to generate a globally coordinated remote operation management scheme. Finally, preliminary fault warning information, power output anomaly alerts, target fault diagnosis commands, the cooperative control strategy balancing fault diagnosis accuracy and power generation efficiency, and the globally coordinated remote operation management scheme are processed to generate comprehensive evaluation information for the hydro-wind-solar coordinated system.

[0009] Another aspect of this application discloses a multi-protocol integrated hydro-wind-solar coordinated control and remote diagnostic device, comprising: an acquisition module for acquiring operating data of core equipment in a hydro-wind-solar power generation system and multi-source environmental parameter information; a processing module for processing the operating data of the core equipment in the hydro-wind-solar power generation system and the multi-source environmental parameter information, combining edge computing nodes to monitor the efficiency of photovoltaic inverters, the wear status of wind turbine gearboxes, the sealing performance of hydro turbines, and the SOC / SOH of energy storage batteries in real time, generating preliminary fault warning information and power output anomaly prompts; processing the preliminary fault warning information and power output anomaly prompts, building a virtual simulation platform for hydro-wind-solar coordinated operation through digital twin technology, simulating the system output characteristics under different fault conditions, and designing hierarchical diagnostic strategies and coordinated scheduling plans by combining multi-objective optimization algorithms. Apply grid security constraints and equipment operation threshold limits to generate target fault diagnosis commands and power coordination allocation schemes. Process the target fault diagnosis commands and power coordination allocation schemes based on corresponding adaptive cooperative control algorithms, dynamically adjust the output ratio of each power generation unit in conjunction with real-time grid load demand and weather forecasts, and generate a cooperative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency. Process the cooperative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency to generate a globally coordinated remote operation management scheme. Process preliminary fault warning information and power output anomaly alerts, target fault diagnosis commands, the cooperative control strategy that balances fault diagnosis accuracy and power generation efficiency, and the globally coordinated remote operation management scheme to generate comprehensive evaluation information for the hydro-wind-solar coordinated system.

[0010] According to another aspect of this application, an electronic device includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-described method for integrated multi-protocol water-wind-solar coordinated control and remote diagnostics by executing the executable instructions.

[0011] According to another aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a second processor, implements the above-described method for integrated multi-protocol water-wind-solar coordinated control and remote diagnostics.

[0012] This application provides a method and related equipment for coordinated control and remote diagnosis of hydro-wind-solar power generation systems integrating multiple protocols. This application constructs a complete technical system encompassing "data acquisition-early warning-diagnosis-control-management-evaluation." It collects core equipment operating data and multi-source environmental parameters through a multi-protocol fusion mechanism, monitors the status of key components via edge computing, and generates preliminary fault warnings and power anomaly alerts. A simulation platform is built using digital twin technology, and a multi-objective optimization algorithm is combined to generate precise diagnostic commands and power allocation schemes. Then, through an adaptive coordinated control algorithm, the power output is dynamically adjusted in conjunction with grid load and meteorological data, forming a coordinated control strategy that considers multiple objectives, thereby generating a global coordinated remote operation and management scheme. Finally, information from all stages is integrated, and a comprehensive evaluation model is constructed using hierarchical analysis and entropy weighting to output multi-dimensional evaluation information such as system reliability and fault handling effectiveness. This application overcomes bottlenecks such as heterogeneous multi-device protocols and insufficient accuracy in fault diagnosis, achieving accurate fault diagnosis, global coordinated control, and efficient remote operation and maintenance, thereby improving the operational reliability and economy of hydro-wind-solar power generation systems.

[0013] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0014] Figure 1 This document illustrates a flowchart of a multi-protocol integrated water, wind, and solar collaborative control and remote diagnostic method provided in an embodiment of this application. Figure 2 This illustration shows a structural schematic diagram of a multi-protocol integrated water, wind, and solar collaborative control and remote diagnostic device provided in an embodiment of this application. Detailed Implementation

[0015] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0016] The following is combined Figure 1 This application describes a method for integrated multi-protocol water, wind, and solar collaborative control and remote diagnostics according to exemplary embodiments thereof. It should be noted that the application scenarios described below are merely illustrative for understanding the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application are applicable to any suitable scenario.

[0017] In one implementation, Figure 1 A schematic flowchart of a multi-protocol integrated water, wind, and solar coordinated control and remote diagnostic method according to an embodiment of this application is shown.

[0018] S101, acquires the operating data of each core device in the hydro-wind-solar power generation system and multi-source environmental parameter information.

[0019] In one implementation, comprehensive data is collected to support equipment status monitoring, fault early warning, collaborative control, and system evaluation. This ensures that the data covers equipment operating status and environmental influencing factors, providing complete and accurate input for subsequent stages. The data includes the actual output of photovoltaic modules (e.g., in a 100MW photovoltaic power plant, output data for modules numbered PV-001 to PV-100 is collected every 5 minutes, ranging from 0-250kW), inverter conversion efficiency (e.g., the real-time conversion efficiency of inverter INV-01, with collected values ​​of 95.2%-98.7%), and module surface temperature (e.g., collected via a temperature sensor integrated into the module, with a value ranging from -10℃ to 65℃).

[0020] Real-time wind turbine speed (e.g., impeller speed of wind turbine WT-05, collected value 12-18 r / min), pitch angle (e.g., pitch angle adjustment range 0°-90°, real-time collected value 15.3°), gearbox operating temperature (e.g., gearbox oil temperature collected value 40℃-85℃), generator output power (e.g., real-time generator output power 0-2.5MW). Turbine inlet flow rate (e.g., inlet flow rate of turbine HL-03, collected value 50-200 m³ / s), head height (e.g., real-time head height 80-120 m), unit output (e.g., actual unit output 10-50 MW), and sealing device operating status parameters (e.g., leakage of seals, collected value 0-5 mL / h).

[0021] The energy storage battery's SOC (State of Charge, e.g., the SOC value of lithium battery pack BAT-02, collected values ​​are 20%-100%), SOH (State of Health, e.g., battery health collected values ​​are 85%-100%), charge and discharge power (e.g., charging power 0-10MW, discharging power 0-10MW), and battery cell voltage (e.g., the voltage of each battery cell is collected values ​​of 3.2-3.7V).

[0022] Solar irradiance in the photovoltaic area (e.g., collected by an irradiance sensor, ranging from 0-1200 W / m²), wind speed (e.g., wind speed in the wind turbine area, collected values ​​from 0-25 m / s), wind direction (e.g., wind direction collected values ​​from 0° to 360°, with due north as 0°), ambient temperature (e.g., ambient temperature collected values ​​for the entire area, ranging from -20°C to 45°C), and precipitation (e.g., daily precipitation collected values ​​from 0-50 mm). Real-time grid frequency (e.g., collected values ​​from 49.5-50.5 Hz), bus voltage (e.g., 110 kV bus voltage collected values ​​from 105-115 kV), and grid load demand (e.g., real-time load of the regional grid, ranging from 50-200 MW). The slope of the photovoltaic power station (e.g., the site slope is collected as 0°-15°), the terrain roughness of the wind turbine deployment area (e.g., the terrain roughness coefficient is 0.15-0.3), and the water level of the hydropower station reservoir (e.g., the real-time water level of the reservoir is 150-180m).

[0023] Dedicated sensors are deployed at key locations on each core piece of equipment to directly collect physical quantity data. For example, temperature sensors are installed on the backsheet of photovoltaic modules and at the oil outlet of the wind turbine gearbox; data is uploaded in real time via the sensors' built-in transmission modules. Equipment operating parameters are exported through the monitoring modules built into devices such as photovoltaic inverters, wind turbine main control systems, and turbine monitoring systems. For example, data such as impeller speed and blade pitch angle are exported from the wind turbine main control system every minute.

[0024] A data acquisition gateway compatible with protocols such as Modbus, IEC61850, and MQTT is employed to enable data exchange and acquisition between different devices and systems. For example, data from photovoltaic inverters (supporting Modbus protocol) and power grid monitoring systems (supporting IEC61850 protocol) are collected through a multi-protocol gateway and aggregated to a unified data acquisition platform. Public data interfaces from regional meteorological stations and power grid dispatch centers are accessed to obtain weather forecast data and power grid load prediction data. For instance, 24-hour irradiance and wind speed prediction data are obtained from local meteorological station interfaces, and 12-hour load demand prediction data are obtained from the power grid dispatch center.

[0025] Core operating parameters (such as equipment output, speed, voltage, and SOC) are acquired at high frequency, every 1-5 minutes. For example, photovoltaic module output and wind turbine speed are collected every minute to ensure real-time capture of changes in equipment operating status. Environmental parameters (such as ambient temperature, irradiance, and grid frequency) are acquired at medium frequency, every 15-30 minutes. For example, solar irradiance and grid voltage are collected every 15 minutes to balance data real-time performance and transmission costs. Parameters with high stability (such as terrain parameters and equipment foundation parameters) are acquired at low frequency, every 1-24 hours or as needed. For example, site slope and reservoir foundation water level are collected daily, while equipment model and rated parameters are collected upon initial deployment and updated as needed thereafter. When equipment operating status fluctuates (such as sudden output changes or temperature exceeding thresholds), the acquisition frequency is automatically increased. For example, when wind turbine speed changes by more than 5 rpm, the acquisition frequency is increased from every minute to every 10 seconds to accurately capture abnormal processes.

[0026] Data of different formats and units collected is uniformly converted. For example, the unit "m³ / min" for turbine inlet flow is converted to "m³ / s", and voltage data from different sensors is uniformly converted to the 0-5V standard range. Based on preset thresholds, obviously abnormal data is removed. For example, if the photovoltaic module temperature reading is -50℃ (outside the reasonable range), it is judged as abnormal data and removed, and the reason for removal is recorded. For missing data due to transmission interruptions, interpolation or prediction based on historical data is used to complete the data. For example, if photovoltaic output data is missing for a certain 5 minutes, linear interpolation is used to complete the data for that period using output data from the preceding and following 10 minutes. The coverage of the collected data is verified to ensure that no key parameters are missed. For example, it is verified whether all preset parameters such as output, efficiency, and temperature of the photovoltaic system have been collected; if inverter efficiency data is missing, a re-collection command is triggered.

[0027] S102 processes the operating data of the core equipment of the hydro-wind-solar power generation system and multi-source environmental parameter information. Combined with the real-time monitoring of photovoltaic inverter efficiency, wind turbine gearbox wear status, water turbine sealing performance and energy storage battery SOC / SOH by edge computing nodes, it generates preliminary fault warning information and power output abnormality prompts.

[0028] In one implementation, based on the status monitoring needs and fault early warning objectives of hydro-wind-solar power generation systems, core equipment operation data and multi-source environmental parameter information are processed. A multi-protocol fusion mechanism is used to extract core parameters such as photovoltaic module output, wind turbine speed, turbine flow rate, and energy storage battery voltage. The data is then categorized and analyzed by equipment type using an edge computing analysis module. Based on monitoring rules, equipment operation thresholds, parameter change rates, and anomaly judgment criteria are extracted and processed to generate a standardized equipment operation dataset, parameter threshold verification information, equipment status code mapping information, and preliminary data anomaly screening results. A fusion mechanism compatible with Modbus, IEC61850, MQTT, and other protocols is employed to accurately extract core parameters from the collected full data, overcoming protocol barriers between different equipment and systems. Photovoltaic module output is extracted from the photovoltaic inverter monitoring system via the Modbus protocol. For example, the real-time output of the PV-021 module in a photovoltaic array is 185kW, with a collection timestamp of 2024-XX-XX 10:30:00.

[0029] The wind turbine speed is extracted from the wind turbine main control system via the IEC61850 protocol. For example, the real-time impeller speed of wind turbine WT-12 is 14.7 r / min, and the synchronously recorded pitch angle is 16.2°. The turbine flow rate is extracted from the hydropower station flow monitoring system via the MQTT protocol. For example, the real-time inflow rate of turbine HL-08 is 125 m³ / s, corresponding to a head height of 98 m. The energy storage battery voltage is extracted from the energy storage management system data integrated through a multi-protocol gateway. For example, the average voltage of individual cells in energy storage battery pack BAT-06 is 3.52 V, and the total voltage is 1056 V.

[0030] The extracted core parameters are transmitted to the edge computing analysis module, where data is broken down into categories based on photovoltaic (PV), wind power, hydropower, and energy storage equipment types to reduce data processing complexity. PV system data is analyzed as follows: parameters such as module output, inverter efficiency, and module temperature are analyzed. For example, eight PV modules with an output below 100kW within the same time period are identified and marked as data to be verified. Wind power system data is analyzed as follows: parameters such as turbine speed, gearbox temperature, and generator power are analyzed by turbine number. For example, analyzing 30 minutes of continuous data for turbine WT-05 reveals that its speed fluctuation range is 12.3-15.1 r / min, which is within the normal operating range.

[0031] Hydropower system data analysis focuses on classifying and processing parameters such as turbine flow rate, head, and unit output. For example, analyzing the flow rate data of turbine HL-03 reveals an average flow rate of 95 m³ / s and a peak flow rate of 180 m³ / s over 24 hours. Energy storage system data analysis follows the same process, classifying and processing parameters such as battery voltage, charge / discharge power, and SOC. For instance, analyzing the voltage data of energy storage battery pack BAT-02 reveals that three individual cells have voltages below 3.2V, marking them as abnormal candidate data.

[0032] Based on equipment manufacturer standards, industry operating specifications, and historical fault data, three core monitoring rules were extracted and standardized. The normal operating ranges for each parameter were clearly defined; for example, the normal threshold for photovoltaic inverter efficiency is 95%-99%, the normal threshold for wind turbine gearbox temperature is 40℃-85℃, and the normal threshold for turbine seal leakage is 0-5mL / h. The allowable variation range of parameters per unit time was set; for example, the maximum allowable variation rate of photovoltaic module output is 10% every 5 minutes, and the maximum allowable variation rate of energy storage battery SOC is 20% per hour.

[0033] Define the criteria for determining whether a parameter exceeds a threshold or its rate of change is abnormal. For example, if a parameter's collected values ​​exceed the normal threshold for three consecutive times, or if its rate of change in a single instance exceeds 1.5 times the allowable range, it is considered abnormal. Based on the above rules, generate a standardized equipment operation dataset (structured data with a unified format and consistent units), parameter threshold verification information (thresholds for each parameter and verification logic), equipment status code mapping information (e.g., "01" represents normal, "02" represents slight abnormality), and preliminary data anomaly screening results (marking 12 suspected abnormal data entries, including equipment number, parameter name, and anomaly type).

[0034] By leveraging the real-time monitoring capabilities of edge computing nodes, standardized datasets and screening results are validated in a targeted manner. The focus is on tracking fluctuations in photovoltaic inverter efficiency, wear levels in wind turbine gearboxes, degradation of turbine sealing performance, and changes in the SOC / SOH ratio of energy storage batteries. Parameters exceeding threshold ranges are marked with anomaly levels. Trend analysis is initiated for data with abnormal rates of change, and a secondary monitoring mechanism is triggered for data with ambiguous status assessments. Preliminary fault warnings and power output anomaly alerts are generated, including anomaly level classifications and monitoring frequency adjustments. The results are then further validated using the real-time computing power of edge computing nodes, with a focus on tracking the status of critical components.

[0035] The efficiency data of the inverter INV-04 is monitored in real time. For example, if the efficiency value fluctuates between 96.2% and 97.8% for one hour without exceeding the threshold, it is considered normal. Indirect monitoring is also conducted through vibration sensor data. For example, monitoring the vibration frequency of the gearbox of the WT-08 fan shows that its vibration frequency increased from the normal 20Hz to 28Hz and lasted for 15 minutes, which is considered a signal of accelerated wear.

[0036] Monitoring changes in seal leakage is crucial. For example, monitoring the seal leakage of the HL-05 water turbine showed an increase from an initial 1.2 mL / h to 6.8 mL / h, exceeding the normal threshold and indicating a decline in sealing performance. Real-time tracking of battery status is also essential. For instance, monitoring the SOC value of the BAT-06 energy storage battery pack revealed a 3% decrease per hour without charging or discharging, with the SOH value dropping to 82%, indicating an anomaly.

[0037] For verified abnormal data, a tiered processing mechanism is adopted to ultimately generate preliminary fault warnings and power output anomaly alerts. Anomalies are categorized into mild, moderate, and severe levels. For example, a wind turbine gearbox temperature reaching 90℃ (exceeding the threshold by 5℃) is marked as a moderate anomaly; a single cell voltage in an energy storage battery dropping to 3.0V (exceeding the threshold by 0.2V) is marked as a severe anomaly. A trend analysis process is initiated. For instance, if the photovoltaic module output drops from 200kW to 150kW within 10 minutes, a change rate of 25% exceeding the allowable range, trend analysis reveals a correlation with a sudden drop in irradiance, generating a warning alert: "Sudden irradiance change leads to abnormal output."

[0038] The secondary monitoring mechanism is triggered. For example, if the turbine flow rate data is 55 m³ / s (close to the lower limit of 50 m³ / s) in a single acquisition, it is impossible to determine whether it is abnormal. A high-frequency secondary monitoring is initiated every minute. If the data collected for five consecutive times is between 53-56 m³ / s, it is considered normal, and the warning is lifted. Finally, a preliminary fault warning is generated, including anomaly level classification (3 mild anomalies, 2 moderate anomalies, and 1 severe anomaly), monitoring frequency adjustment (increasing the monitoring frequency from 5 minutes / time to 1 minute / time for equipment with moderate or higher anomalies), and 2 power output anomaly alerts (wind turbine WT-08 experiences a 10% power reduction due to gearbox wear, and energy storage battery pack BAT-06 experiences insufficient discharge power due to SOC abnormality).

[0039] S103 processes preliminary fault warning information and power output anomaly alerts, builds a virtual simulation platform for coordinated operation of water, wind and solar power through digital twin technology, simulates the system output characteristics under different fault conditions, designs hierarchical diagnosis strategies and coordinated scheduling plans by combining multi-objective optimization algorithms, applies grid safety constraints and equipment operation threshold limits, and generates target fault diagnosis instructions and power coordination allocation schemes.

[0040] In one implementation, based on the core characteristics of digital twin technology—virtual-real mapping and real-time interaction—preliminary fault warning information, power output anomaly alerts, historical equipment operating data, and environmental baseline parameters are categorized and integrated to generate a basic dataset for twin modeling that includes fault type, anomaly level, and impact range. Relying on the core characteristics of digital twin technology—virtual-real mapping and real-time interaction—multi-source correlated data is categorized and integrated to provide complete data support for virtual simulation modeling. Preliminary fault warning information includes abnormal equipment components and suspected fault causes, such as abnormal vibration warnings for the wind turbine WT-08 gearbox and SOC attenuation warnings for the energy storage battery pack BAT-06. Power output anomaly alerts record the output deviation of each power generation unit; for example, the output of photovoltaic arrays PV-021 to PV-030 is 15% lower than the rated value, and the output fluctuation of the water turbine HL-05 exceeds 8%.

[0041] The historical operating data of the equipment is as follows: Operating parameters and fault repair records for the past year were extracted. For example, the gearbox temperature change curve of the WT-08 wind turbine over the past three months and the charge / discharge cycle count (1200 times) of the BAT-06 energy storage battery pack. Environmental baseline parameters are as follows: Standard values ​​and fluctuation ranges for normal operating environments were set, for example, standard irradiance of the photovoltaic area is 800-1000 W / m², standard wind speed of the wind turbine area is 5-12 m / s, and standard grid frequency is 50 Hz ± 0.2 Hz.

[0042] After integration, a structured twin modeling base dataset is formed, which includes fault type (gearbox wear, SOC decay, insufficient output, etc.), anomaly level (mild, moderate, severe), and impact range (single device, single power generation unit, entire system). For example, "Fault type: wind turbine gearbox wear; anomaly level: moderate; impact range: wind power unit output decreases by 10%".

[0043] Based on simulation accuracy requirements, the functional modules of the virtual simulation platform for coordinated operation of hydropower, wind power, and solar power are designed. The configuration proportions of equipment simulation models, operating condition simulation engines, and output prediction algorithms are clarified, generating platform architecture design information. Combining multi-objective optimization algorithms and system safety operation requirements, diagnostic and scheduling rules are set based on fault severity levels and dynamic adjustments according to grid constraints to ensure the synergy between fault handling and power allocation. The core functional modules and their configuration proportions are clearly defined to ensure that simulation accuracy meets the requirements of fault simulation and strategy optimization. Equipment simulation models (40%): Virtual models of photovoltaic, wind power, hydropower, and energy storage equipment are constructed at a 1:1 scale to reproduce the equipment structure and operating characteristics. For example, a virtual model of a wind turbine gearbox is built to accurately map physical processes such as gear meshing and bearing rotation; a virtual model of photovoltaic modules is constructed to correlate the quantitative relationship between irradiance, temperature, and output.

[0044] Operating Condition Simulation Engine (30%): Capable of simulating various operating conditions including normal, fault, and extreme environments. For example, simulating accelerated wear of wind turbine gearboxes, sudden drop in irradiance in photovoltaic areas, and sudden increase in grid load. Output Prediction Algorithm (30%): Integrates machine learning and numerical calculation algorithms to predict system output under different operating conditions. For example, using the LSTM algorithm to predict the output of a photovoltaic array for the next two hours, and using fluid dynamics algorithms to predict the output of a water turbine under different flow rates.

[0045] Generate platform architecture design information, clarify the interface specifications, data transmission paths and computing power configurations of each module. For example, the equipment simulation model and the working condition simulation engine interact through a standardized data interface with a data transmission latency of ≤50ms; configure a 16-core CPU and 256GB of memory to support simulation calculations.

[0046] Based on multi-objective optimization algorithms (NSGA-III (Non-dominated sorting genetic algorithm III), MOPSO (Multi-objective particle swarm optimization algorithm), and MOEA / D (Decomposition-based multi-objective evolutionary algorithm)) (balancing fault diagnosis accuracy, power supply stability, and operation and maintenance costs) and system safety operation requirements, hierarchical diagnosis and dynamic scheduling rules are formulated. Faults are classified into levels according to severity, and corresponding diagnostic processes are set. For example, taking NSGA-III (Non-dominated sorting genetic algorithm III) as an example, the "output ratio of each power generation unit, fault diagnosis process selection, and operation and maintenance resource allocation scheme" are encoded as chromosomes (individuals), and N initial individuals are randomly generated to form an initial population (covering different combinations of fault handling and power allocation).

[0047] For each individual, three target values ​​are calculated: fault diagnosis accuracy: based on the results of digital twin simulation, the fault location deviation rate is calculated (the smaller the deviation, the higher the accuracy); power supply stability: quantify the amplitude of grid frequency / voltage fluctuations and the duration of system output gaps (the smaller the fluctuations and the shorter the gaps, the more stable the system); operation and maintenance cost: calculate the comprehensive cost of fault handling manpower, materials, downtime losses, etc. (the lower the value, the better).

[0048] Individuals in the population are classified according to their objective function values. The individual with the best overall performance is classified as the "non-dominated solution" (first frontier layer), and the rest are classified according to their dominance relationship to ensure that individuals with better overall performance are retained first.

[0049] Set up uniformly distributed reference points, calculate the Euclidean distance between each individual and the reference points, and prioritize individuals with close and uniform distances to avoid solutions concentrating in local areas and ensure solution diversity (such as differentiated strategies for different fault levels). Select, crossover, and mutate the retained individuals (e.g., adjust the output ratio of a power generation unit, change the fault diagnosis process) to generate a new generation population, ensuring the algorithm explores new solution spaces. Repeat the above steps until the number of iterations reaches a threshold or the objective function value converges. Finally, select solutions that balance the three objectives from the optimal frontier layer, transforming them into hierarchical diagnosis strategies (such as processes corresponding to mild / moderate / severe anomalies) and dynamic power allocation schemes (such as output adjustment rules under grid constraints).

[0050] The system processes the twin modeling dataset, platform architecture design information, and hierarchical scheduling rules to generate target fault diagnosis instructions and power coordination allocation schemes that include model parameters, simulation procedures, diagnostic criteria, and allocation strategies. It clarifies fault location, diagnostic procedures, and verification standards. For example, "Faulty equipment: Wind turbine WT-08; Fault location: Gearbox bearing wear; Diagnostic procedure: 1. Virtual simulation of vibration characteristics at different stages of bearing wear; 2. Comparison of measured data with simulation results; 3. Output of quantitative assessment of wear degree; Verification standard: Deviation between diagnostic results and actual disassembly and inspection ≤ 5%."

[0051] Formulate output adjustment strategies for each power generation unit. For example, "The grid load is 180MW, and the faulty wind turbine WT-08 is shut down for maintenance (rated output 2.5MW); Adjustment plan: increase the output of the photovoltaic array to 95% of the rated value (originally 80%), increase the output of the water turbine HL-05 by 3MW (originally 45MW → 48MW), and discharge the energy storage battery pack BAT-06 with an output of 2.5MW to make up for the fault gap and ensure that the total system output is stable at 180MW±2%."

[0052] The core content of the solution includes model parameters (physical parameters and algorithm coefficients of the virtual simulation model), simulation process (operating condition simulation steps and data comparison logic), diagnostic criteria (fault judgment threshold and accuracy requirements), and allocation strategy (output adjustment range and priority order) to ensure the operability and accuracy of the instructions and the solution.

[0053] S104 processes the target fault diagnosis command and power coordination allocation scheme based on the corresponding adaptive cooperative control algorithm, and dynamically adjusts the output ratio of each power generation unit in combination with real-time grid load demand and weather forecast, generating a cooperative control strategy that takes into account fault diagnosis accuracy, power supply stability and power generation efficiency.

[0054] In one implementation, core input information is obtained based on the collaborative control objective, and fault handling requirements and output benchmark ratios in the power coordination allocation scheme are extracted from the target fault diagnosis command. Guided by the collaborative control objective (considering fault diagnosis accuracy, power supply stability, and power generation efficiency), key information is extracted from the previous output results to provide a core basis for strategy generation. The fault handling requirements in the target fault diagnosis command are extracted: the handling method, priority, and diagnostic coordination requirements of the faulty equipment are clarified. For example, "Faulty equipment: Wind turbine WT-08 (gearbox bearing wear, moderate abnormality); Handling requirements: priority should be given to operation and maintenance, and the output of this wind turbine should be limited to ≤500kW during the maintenance period. A fault diagnosis data acquisition channel needs to be reserved."

[0055] Extract the output baseline ratio in the power coordination and allocation scheme: obtain the basic output ratio of each power generation unit under normal operation and fault conditions. For example, "when the total grid load is 200MW, the output baseline ratio is: photovoltaic 40% (80MW), wind power 30% (60MW), hydropower 25% (50MW), energy storage 5% (10MW); after the WT-08 wind turbine fails, the wind power baseline ratio is adjusted to 27.5% (55MW)".

[0056] The extracted core information undergoes compliance verification to confirm the feasibility of fault handling requirements and the rationality of the output baseline ratio, generating information verification results. Fault handling requirement feasibility verification: Based on equipment maintenance resources and system operating status, the feasibility of the handling plan is determined. For example, verifying the requirement of "priority maintenance of wind turbine WT-08," if it is confirmed that the maintenance team can arrive on-site within 2 hours and the backup wind turbine can temporarily supplement power, it is deemed feasible; if the maintenance team needs to arrive after 24 hours and there is no backup power equipment, it is deemed temporarily infeasible, and the handling priority needs to be adjusted.

[0057] Verify the rationality of the ratio by comparing it with the rated capacity of the equipment, grid constraints, and environmental conditions. For example, verify the baseline ratio of 40% (80MW) for photovoltaics. If the rated total output of the photovoltaic array is 100MW and the current irradiance supports full power generation, it is considered reasonable. If the current irradiance can only support the maximum output of photovoltaics of 60MW, the ratio is considered unreasonable and the baseline ratio needs to be lowered to 30% (60MW).

[0058] Generate information verification results, clearly identifying qualified and unqualified items and adjustment suggestions. For example, "Qualified items: WT-08 wind turbine fault handling requirements, hydropower and energy storage output benchmark ratio; Unqualified items: original 40% photovoltaic output benchmark ratio (currently insufficient irradiance); Adjustment suggestion: reduce the photovoltaic benchmark ratio to 30%."

[0059] Based on the dynamic adjustment characteristics of the adaptive cooperative control algorithm, the core information of the verification is integrated and analyzed to generate the algorithm input parameter set. The fault-related parameters include the faulty equipment number, fault type, handling priority, and limited output value. For example, "Faulty equipment number: WT-08; Fault type: Gearbox wear; Handling priority: Level 2 (medium); Limited output value: ≤500kW".

[0060] Output baseline parameters are used to integrate the adjusted output baseline ratios and corresponding power values ​​of each unit, for example, "Photovoltaics: 30% (60MW), Wind Power: 27.5% (55MW), Hydropower: 25% (50MW), Energy Storage: 17.5% (35MW)". Constraint correlation parameters are used to correlate the logical relationship between fault handling and output adjustment, for example, "During the overhaul of wind turbine WT-08, the energy storage output can be dynamically adjusted within the range of 10-35MW to make up for the wind power output gap". The final algorithm input parameter set is presented in a structured form to ensure that the parameters are complete, the logic is clear, and it is adapted to the dynamic adjustment requirements of the algorithm.

[0061] By combining real-time grid load demand and short-term meteorological forecast data, the output regulation boundaries of photovoltaic, wind power, hydropower, and energy storage units are clarified, and unit regulation constraint information is generated. Real-time grid load demand: The current and next 1-2 hour grid load conditions are clearly defined, for example, "Current grid load is 180MW, expected to rise to 190MW in the next hour, grid frequency allowable fluctuation range 49.5-50.5Hz, voltage allowable fluctuation range 105-115kV." Key meteorological information for photovoltaic and wind power areas is obtained, for example, "In the next 2 hours, the irradiance in the photovoltaic area will remain at 600-700W / m², the wind speed in the wind turbine area will remain at 6-8m / s, and there will be no extreme weather."

[0062] Based on the above data, the maximum and minimum output values ​​are clearly defined. For example, "Photovoltaic: minimum output 30MW, maximum output 70MW; Wind power (excluding faulty units): minimum output 40MW, maximum output 55MW; Hydropower: minimum output 40MW, maximum output 60MW; Energy storage: minimum output 10MW, maximum output 35MW." The adjustment range and related conditions of each unit are also clearly defined. For example, "Photovoltaic output varies with irradiance, adjusting within the range of 30-70MW; when the grid load rises to 190MW, hydropower can be increased to full capacity of 60MW."

[0063] Based on multi-objective optimization logic, dynamic adjustment rules are set, and the output ratio is optimized in layers according to fault handling priority, power supply stability requirements, and power generation efficiency targets to generate a proportional adjustment scheme. The layer priority is set as follows: First layer (highest): fault handling priority (ensuring faulty equipment diagnosis and maintenance); Second layer: power supply stability requirements (maintaining grid frequency and voltage stability); Third layer: power generation efficiency target (maximizing the use of renewable energy and reducing energy consumption).

[0064] The tiered optimization of power output ratios is as follows, meeting fault handling priorities: limiting the output of the faulty wind turbine WT-08 to ≤500kW, and adjusting the output of other wind power units to 54.5MW (close to the baseline value of 55MW). Meeting power supply stability requirements: with the current grid load at 180MW, power output is allocated according to the adjustment boundaries: 60MW photovoltaic (irradiance-adaptive), 54.5MW wind power, 50MW hydropower, and 15.5MW energy storage, for a total output of 180MW, maintaining a grid frequency of 50Hz and a voltage of 110kV. Meeting power generation efficiency targets: prioritizing the increase of photovoltaic and wind power output (renewable energy). When irradiance rises to 700W / m², photovoltaic output is adjusted to 70MW, and energy storage output is reduced to 5MW, maintaining stable total output and improving overall power generation efficiency.

[0065] Generate a proportional adjustment scheme, clarifying the output allocation ratio and adjustment logic for each scenario. For example, "Conventional scenario: PV 33.3%, wind power 30.3%, hydropower 27.8%, energy storage 8.6%; Irradiation enhancement scenario: PV 38.9%, wind power 30.3%, hydropower 27.8%, energy storage 3.0%."

[0066] An iterative update mechanism is established to adjust regulation parameters in real time based on grid load fluctuations and changes in actual weather conditions, generating a coordinated control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency. Iterative update trigger conditions are set: grid load fluctuations exceeding ±5%, deviations between actual and predicted weather conditions exceeding ±20%, and changes in fault status (such as fault resolution or new faults). For example, "Grid load increases from 180MW to 190MW (fluctuation of 5.6%), and photovoltaic irradiance increases from 600W / m² to 750W / m² (deviation of 25%), triggering an iterative update." Regulation parameters are adjusted based on these trigger conditions. For example, "Grid load increases to 190MW, irradiance increases to 750W / m²; adjusted output: photovoltaic 70MW, wind power 54.5MW, hydropower 60MW, energy storage 5.5MW, total output 190MW, meeting power supply stability and efficiency targets."

[0067] Integrate all optimization results, clarify fault diagnosis coordination requirements, power output adjustment rules for each unit, and iterative update mechanism. For example, "Fault diagnosis coordination: retain the WT-08 data acquisition channel and upload operating parameters every 5 minutes; power output adjustment rules: photovoltaic power is adjusted between 30-70MW according to irradiance, hydropower is adjusted between 40-60MW, and energy storage is dynamically replenished; update mechanism: automatic iteration when load fluctuation exceeds ±5% or irradiance deviation exceeds ±20%".

[0068] S105 processes the collaborative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency, generating a globally collaborative remote operation management scheme.

[0069] In one implementation, multi-dimensional core elements of the collaborative control strategy are extracted. This involves analyzing the output adjustment parameters, fault handling priorities, power supply stability thresholds, and power generation efficiency targets of each power generation unit. Regional coordination logic and equipment linkage rules within the strategy are identified, generating a set of elements to be integrated, including unit control characteristics and system collaboration characteristics. Key elements are extracted from the collaborative control strategy to clarify the control requirements of each unit and the system collaboration logic, laying the foundation for a comprehensive management plan. Core parameters for each power generation unit are extracted, specifically as follows, clarifying the output adjustment range, step size, and associated conditions for each unit. For example, "Photovoltaic unit: adjustment range 30-70MW, step size 5MW, adjusted once every 100W / m² change in irradiance; Hydropower unit: adjustment range 40-60MW, step size 10MW, triggered when grid load fluctuation exceeds ±5%."

[0070] Prioritize different faults according to their handling order, for example, "Priority 1: Severe abnormality of energy storage battery (single cell voltage <3.0V), turbine seal leakage exceeding 10mL / h; Priority 2: Moderate wear of wind turbine gearbox, photovoltaic inverter efficiency below 95%; Priority 3: Slight deviation in module output, minor fluctuation of environmental parameters." Set permissible ranges for key grid operation indicators, for example, "Grid frequency stability threshold 49.5-50.5Hz, voltage stability threshold 105-115kV, system output fluctuation threshold ±2%." Clarify the efficiency requirements for each unit and the overall system, for example, "Photovoltaic inverter efficiency ≥95%, wind turbine power generation efficiency ≥80%, overall system power generation efficiency ≥85%."

[0071] The regional coordination logic and equipment linkage rules are identified as follows: The coordination method between cross-regional power generation units is clarified. For example, "When the photovoltaic output of region A is insufficient, energy storage in the same region is prioritized for supplementation, and the remaining portion is supplemented by hydropower from region B; during peak grid load, hydropower and energy storage in all regions are given priority for output, while photovoltaic and wind power operate at maximum efficiency." The linkage triggering conditions and operations between different devices are defined. For example, "When a wind turbine shuts down due to low wind speed, the corresponding regional energy storage is automatically activated for discharge; when a sudden drop in photovoltaic irradiance causes a power output decrease of more than 20%, the turbine output is simultaneously increased by 10%-15%." The above information is integrated to form a structured set containing unit control characteristics (such as adjustment parameters and fault priorities for each unit) and system coordination characteristics (such as regional coordination logic and equipment linkage rules), ensuring that no elements are omitted and the logic is clear.

[0072] Based on the need for global collaborative management, the system comprehensively processes the set of elements, achieves compatible transmission of cross-regional control commands through a remote communication protocol adaptation algorithm, and allocates operation and maintenance resources for each region using a resource optimization allocation model. This generates global collaborative processing results and evaluation information covering protocol compatibility and resource allocation rationality. The remote communication protocol adaptation algorithm enables interoperability of commands between different regions and devices. For example, "using a protocol adaptation algorithm compatible with Modbus (photovoltaic equipment), IEC61850 (grid equipment), and MQTT (energy storage equipment) protocols, the energy storage discharge command in region A is converted into a power adjustment command recognizable by the hydropower equipment in region B, with a transmission delay ≤100ms." The resource optimization allocation model rationally allocates operation and maintenance resources such as manpower and materials. For example, "based on the fault level and number of devices in each region, the operation and maintenance team is allocated: region C, with concentrated faults, is allocated 2 groups of operation and maintenance personnel and 1 emergency repair vehicle; region D, without severe faults, is allocated 1 group of operation and maintenance personnel, with material support prioritized for the fault area."

[0073] Clearly define the command transmission path and resource allocation scheme. For example, "Command transmission path: Control Center → Regional Gateway → Equipment Terminal; Resource allocation scheme: 3 groups of maintenance personnel, 2 emergency repair vehicles, and 5 sets of spare parts, deployed in areas C, A, and B respectively." Evaluation information includes protocol compatibility (e.g., "Modbus and IEC61850 protocol compatibility 98%)" and the rationality of resource allocation (e.g., "Resource satisfaction rate in area C is 100%, resource utilization rate in area D is 85%)," providing a basis for subsequent optimization.

[0074] Based on the assessment information, targeted optimizations were performed. Interface debugging mechanisms were used to adjust protocol compatibility deviations, dynamic scheduling algorithms were applied to correct resource allocation imbalances, and the matching degree between collaborative logic and device response was re-verified for command interaction anomalies, generating an optimized global collaborative solution. The interface debugging mechanism was used to resolve compatibility issues between different protocols. For example, "a compatibility deviation was found between the MQTT protocol and some older energy storage devices (compatibility rate 82%). By debugging interface parameters and updating the communication module firmware, the compatibility rate was improved to 97%."

[0075] A dynamic scheduling algorithm based on an improved genetic algorithm is used to adjust the distribution of operation and maintenance resources. This algorithm encodes operation and maintenance resources (personnel, equipment, and materials) and fault tasks, and constructs an objective function that includes resource constraints and regional distance constraints, with the shortest fault handling response time and the highest resource utilization rate as the optimization objectives. The optimal resource allocation scheme is solved iteratively through selection, crossover, and mutation operations. For example, the assessment found that two wind turbines in area E experienced moderate faults (abnormal gearbox vibration and decreased generator insulation). The originally allocated one group of operation and maintenance personnel and one set of detection equipment could not complete the handling of the two faults within 4 hours, resulting in a significant resource gap. Through real-time calculation of operation and maintenance resources across the entire region using this dynamic scheduling algorithm, it was identified that there were currently no severe fault tasks in area D. The one group of operation and maintenance personnel with wind turbine fault handling experience and one set of vibration detection equipment allocated to area D were idle, and the travel time between area D and area E was only 30 minutes. The algorithm automatically generates scheduling instructions to temporarily relocate the group of personnel and equipment to area E, while updating the resource backup plan for area D (with emergency support provided by the maintenance team in the adjacent area F). Ultimately, the dual faults in area E are resolved within 3.5 hours, ensuring that the faults do not spread and do not affect the stability of the area's power supply, which is consistent with the logic of "optimized resource allocation and dynamic adaptation to fault requirements" in global collaborative management.

[0076] Re-examine the matching degree between the coordination logic and the equipment response. For example, "It was detected that the photovoltaic output adjustment command and the wind turbine linkage response were out of sync (delay of 150ms). The linkage rules were re-verified, the command triggering sequence was optimized, and the synchronization delay was shortened to within 50ms."

[0077] An optimized global collaboration solution is generated, integrating and adjusting protocol adaptation methods, resource allocation schemes, and command interaction logic to form a more complete collaboration solution, ensuring smooth connection between all links.

[0078] The integrated and optimized global collaboration solution undergoes final verification based on the real-time and reliability requirements of remote operation and maintenance, generating a global collaborative remote operation and management solution that includes remote communication specifications, resource scheduling procedures, emergency response plans, and a global coordination mechanism. The optimized collaboration solution is then finalized to ensure it meets the real-time and reliability requirements of remote operation and maintenance, forming a feasible management solution. The final verification includes the following: Real-time verification: testing the speed of command transmission, resource scheduling, and fault response. For example, "remotely issuing energy storage charging commands, equipment response time ≤ 200ms; dispatching operation and maintenance resources to the fault site, response time ≤ 1 hour." Reliability verification: simulating extreme conditions (such as simultaneous faults in multiple areas, communication interference) to test the solution's stability. For example, "simulating simultaneous minor faults in three areas, the solution can still reasonably allocate resources and issue commands normally, without command loss or resource conflicts."

[0079] Generate a global collaborative remote operation and management solution, comprising four core components to ensure coverage of all remote operation and maintenance scenarios: Clearly define protocol types, interface parameters, transmission rates, and fault tolerance mechanisms. For example, "Prioritize the IEC61850 protocol, with a transmission rate ≥10Mbps, automatic switching to a backup channel during communication interruptions, and a data loss rate ≤0.1%." Define the steps and triggering conditions for resource application, allocation, scheduling, and reclamation. For example, "The faulty area submits a resource application → the control center assesses the need → dynamically schedules idle resources → reclaims resources after fault handling, with full scheduling traceability." Clearly define the response process, handling measures, and responsible persons for different levels of faults. For example, "Severe faults: immediately issue a shutdown order → schedule nearby operation and maintenance resources → arrive on-site for handling within 1 hour; Minor faults: remote data review → issue adjustment orders → continuously monitor the handling effect." Standardize cross-regional and cross-device collaboration rules. For example, "Establish a regional coordination committee and hold monthly coordination meetings; set up a global scheduling center to monitor the operational status of each region in real time and coordinate cross-regional resources and instructions uniformly."

[0080] S106 processes preliminary fault warning information, power output anomaly prompts, target fault diagnosis instructions, collaborative control strategies that balance fault diagnosis accuracy and power generation efficiency, and global collaborative remote operation management schemes to generate comprehensive evaluation information for the hydro-wind-solar collaborative system.

[0081] In one implementation, a comprehensive evaluation index system is used to integrate preliminary fault warning information, power output anomaly alerts, target fault diagnosis commands, collaborative control strategies, and remote operation management schemes to generate a multi-dimensional evaluation dataset. Using the comprehensive evaluation index system as a framework, key information from the entire process is integrated to ensure the dataset covers the core dimensions of system operation. The evaluation index system framework includes four core dimensions and twelve specific indicators, such as: "fault diagnosis dimension (fault warning accuracy, diagnostic command precision), power supply stability dimension (frequency fluctuation rate, voltage deviation rate, output stability), power generation efficiency dimension (equipment efficiency, overall system efficiency, renewable energy utilization rate), and management optimization dimension (resource allocation efficiency, protocol compatibility, emergency response speed, energy saving benefits)."

[0082] Extract the number of warnings, the distribution of anomaly levels, and the warning response time. For example, "3 mild anomalies, 2 moderate anomalies, and 1 severe anomaly; average warning response time 8 minutes." Summarize the output deviation value and the duration of the anomaly. For example, "Wind turbine WT-08 output deviation 10%, lasting 2 hours; photovoltaic array output deviation 5%, lasting 30 minutes." Statistically analyze the number of diagnostics and the consistency between diagnostic results and actual faults. For example, "6 diagnostic commands, 5 consistent with the actual fault, 1 deviation."

[0083] Extract output adjustment accuracy and strategy iteration count, for example, "output adjustment accuracy 92%, updated 3 times due to load fluctuations". Record resource scheduling success rate and communication transmission stability, for example, "resource scheduling success rate 95%, communication data loss rate 0.08%".

[0084] Generate a multi-dimensional evaluation dataset and integrate the above data in a structured table format, clearly specifying the indicator name, data source, value, and unit. For example, "Indicator name: Fault warning accuracy rate; Data source: Preliminary fault warning information; Value: 93.3%; Unit: %".

[0085] An algorithm combining the Analytic Hierarchy Process (AHP) and the entropy weight method is used to quantify the features of the evaluation dataset and construct a comprehensive evaluation model of the system's operating status. The AHP determines subjective weights, clarifying the relative importance of each indicator through expert scoring; for example, "fault diagnosis accuracy weight 0.25, power supply stability coefficient weight 0.25, power generation efficiency value weight 0.2, resource allocation rationality weight 0.15, and energy-saving benefit quantification value weight 0.15." The entropy weight method determines objective weights, adjusting the subjective weights based on the information entropy calculation of the evaluation dataset; for example, "fault diagnosis accuracy objective weight 0.23, power supply stability coefficient objective weight 0.27, power generation efficiency value objective weight 0.22, resource allocation rationality weight 0.14, and energy-saving benefit quantification value weight 0.14."

[0086] Qualitative indicators such as "rationality of resource allocation" and "effectiveness of emergency response" are assigned scores of 4, 3, 2, and 1 respectively, categorized as excellent, good, average, and poor. For example, "Rationality of resource allocation: Good, assigned 3 points." The extreme value method is used to uniformly map indicators of different magnitudes to the 0-1 range. For example, "The original range of power generation efficiency was 80%-90%, and after standardization, the value of a certain system is 0.85; the original range of fault diagnosis accuracy was 90%-95%, and after standardization, it is 0.67."

[0087] A comprehensive evaluation model is constructed, integrating weights and quantified indicators to form a calculation model of "comprehensive evaluation value = Σ (standardized indicator value × combined weight)". The combined weight is a weighted average of subjective and objective weights (each weight accounts for 50%).

[0088] By combining industry standard thresholds with actual operational needs, the weighting coefficients and judgment criteria of the evaluation model are iteratively optimized to generate a calibration set of evaluation parameters. Examples of industry standard thresholds are as follows: "Fault diagnosis accuracy ≥ 90%, power supply stability coefficient ≥ 0.95, power generation efficiency ≥ 85%, and energy-saving benefit quantification value ≥ 5%."

[0089] The judgment criteria are revised based on system scale and operating environment. For example, "for wind power systems in high-altitude areas, the judgment criteria for power supply stability coefficient are lowered to ≥0.93; for large-scale photovoltaic bases, the judgment criteria for power generation efficiency are raised to ≥88%." Based on historical assessment data and actual operating results, the combined weights are adjusted. For example, "it was found that energy-saving benefits have a greater impact in actual operation, so its combined weight is increased from 0.14 to 0.18, while the weight of fault diagnosis accuracy is simultaneously lowered to 0.21."

[0090] Generate an evaluation parameter calibration set: Define the optimized weight coefficients and the judgment criteria for each indicator (excellent, good, average, and poor thresholds), for example, "fault diagnosis accuracy: excellent ≥94%, good 90%-94%, average 85%-90%, poor <85%; combined weight: 0.21".

[0091] Based on the calibration set of evaluation parameters, comprehensive calculations are performed on multi-dimensional indicator data to generate preliminary evaluation results including fault diagnosis accuracy, power supply stability coefficient, and power generation efficiency. Based on the calibrated evaluation parameters, calculations are performed on the multi-dimensional indicator data to obtain preliminary evaluation values ​​for the core indicators. The fault diagnosis accuracy is calculated as follows: (Number of correct diagnoses / Total number of diagnoses) × 100%. For example, "5 correct diagnoses, 6 total diagnoses, calculated as 83.3%".

[0092] The power supply stability coefficient is calculated based on frequency and voltage fluctuations, using the formula "1 - (duration of frequency fluctuation exceeding the standard + duration of voltage fluctuation exceeding the standard) / total operating time". For example, "total duration of exceeding the standard is 0.5 hours, total operating time is 24 hours, calculated as 0.979". The power generation efficiency value is calculated as follows: total system power generation / total input energy consumption × 100%. For example, "total power generation is 450MWh, total input energy consumption is 500MWh, calculated as 90%".

[0093] Generate preliminary assessment results, present the core indicator assessment values ​​in numerical form, and clarify the indicator level, such as "fault diagnosis accuracy rate 83.3% (medium), power supply stability coefficient 0.979 (excellent), power generation efficiency value 90% (good)".

[0094] The preliminary assessment results, quantitative data of indicators, and parameter calibration information are collaboratively verified to generate comprehensive assessment information for the hydro-wind-solar coordinated system, covering system reliability level, fault handling effectiveness, resource allocation rationality, and quantified energy-saving benefits. The logical consistency between the preliminary assessment results and the original data is verified; for example, "the fault diagnosis accuracy calculation is based on 5 correct diagnoses, and the original data shows 5 correct diagnoses, with no data contradiction." The assessment results are confirmed to meet the calibrated judgment criteria; for example, "the power generation efficiency value of 90% falls within the 'good' threshold range (88%-92%), and the adaptability meets the standard." The impact of weight allocation on the final result is verified to be reasonable; for example, "after adjusting the energy-saving benefit weights, the change in the comprehensive assessment value is ≤5%, indicating that the weight setting is reasonable."

[0095] Generate comprehensive evaluation information, integrate and verify the results, and form multi-dimensional evaluation conclusions, such as "System reliability level: Level 2; Fault handling effectiveness: Good (83.3%); Resource allocation rationality: Good (3 points); Power supply stability coefficient: Excellent (0.979); Power generation efficiency value: Good (90%); Energy saving benefit quantification value: 6.2%", to ensure that the information covers the core performance of system operation and provides a clear basis for subsequent optimization.

[0096] In one implementation, such as Figure 2 As shown, this application also provides a multi-protocol integrated water, wind, and solar collaborative control and remote diagnostic device, including: Module 201 is used to acquire the operating data of each core device of the hydro-wind-solar power generation system and multi-source environmental parameter information; Processing module 202 is used to process the operating data of core equipment and multi-source environmental parameters of the hydro-wind-solar power generation system. It combines real-time monitoring of photovoltaic inverter efficiency, wind turbine gearbox wear status, turbine sealing performance, and energy storage battery SOC / SOH by edge computing nodes to generate preliminary fault warning information and power output anomaly alerts. After processing the preliminary fault warning information and power output anomaly alerts, a virtual simulation platform for coordinated operation of hydro-wind-solar power generation is built using digital twin technology to simulate the system output characteristics under different fault conditions. A hierarchical diagnosis strategy and coordinated scheduling plan are designed using multi-objective optimization algorithms, applying grid safety constraints and equipment operating threshold limits, and generating target fault diagnosis instructions and power coordination instructions. The system is configured with the following steps: Based on the corresponding adaptive cooperative control algorithm, the target fault diagnosis command and power coordination allocation scheme are processed. The output ratio of each power generation unit is dynamically adjusted in combination with real-time grid load demand and weather forecast, generating a cooperative control strategy that takes into account fault diagnosis accuracy, power supply stability and power generation efficiency. The cooperative control strategy that takes into account fault diagnosis accuracy, power supply stability and power generation efficiency is processed to generate a globally coordinated remote operation management scheme. The preliminary fault warning information and power output anomaly prompts, target fault diagnosis commands, the cooperative control strategy that takes into account fault diagnosis accuracy and power generation efficiency and the globally coordinated remote operation management scheme are processed to generate comprehensive evaluation information of the hydro-wind-solar coordinated system.

[0097] The computer-readable storage medium provided in the above embodiments of this application and the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0098] The various embodiments in this application are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for evaluating the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method, electronic device, electronic device, and readable storage medium are basically similar to the embodiments of the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method described above, and are therefore described simply. Relevant parts can be referred to in the descriptions of the embodiments of the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method described above.

Claims

1. A method for integrated multi-protocol water-wind-solar coordinated control and remote diagnostics, characterized in that, include: Acquire operational data and multi-source environmental parameter information of core equipment in hydro, wind and solar power generation systems; The system processes the core equipment operation data and multi-source environmental parameter information of the hydro-wind-solar power generation system, and combines edge computing nodes to monitor the photovoltaic inverter efficiency, wind turbine gearbox wear status, water turbine sealing performance and energy storage battery SOC / SOH in real time to generate preliminary fault warning information and power output abnormality prompts. The system processes preliminary fault warning information and power output anomaly alerts, builds a virtual simulation platform for coordinated operation of water, wind and solar power through digital twin technology, simulates the system output characteristics under different fault conditions, designs hierarchical diagnosis strategies and coordinated scheduling plans by combining multi-objective optimization algorithms, applies grid safety constraints and equipment operation threshold limits, and generates target fault diagnosis instructions and power coordination allocation schemes. Based on the corresponding adaptive cooperative control algorithm, the target fault diagnosis command and power coordination allocation scheme are processed. Combined with real-time grid load demand and weather forecast, the output ratio of each power generation unit is dynamically adjusted to generate a cooperative control strategy that takes into account fault diagnosis accuracy, power supply stability and power generation efficiency. The collaborative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency is processed to generate a globally collaborative remote operation management scheme. The system processes preliminary fault warning information, power output anomaly alerts, target fault diagnosis instructions, collaborative control strategies that balance fault diagnosis accuracy and power generation efficiency, and global collaborative remote operation management schemes to generate comprehensive evaluation information for the hydro-wind-solar collaborative system.

2. The method as described in claim 1, characterized in that, The system processes operational data from core equipment in hydro-wind-solar power generation systems, along with multi-source environmental parameters. It combines this data with real-time monitoring of photovoltaic inverter efficiency, wind turbine gearbox wear, hydro turbine sealing performance, and energy storage battery SOC / SOH using edge computing nodes. This generates preliminary fault warnings and power output anomaly alerts, including: Based on the status monitoring needs and fault early warning objectives of hydro-wind-solar power generation systems, the system processes the core equipment operation data and multi-source environmental parameter information. It adopts a multi-protocol fusion mechanism to extract core parameters such as photovoltaic module output, wind turbine speed, hydro turbine flow rate, and energy storage battery voltage. The system uses an edge computing analysis module to classify and parse the data according to equipment type. Based on the monitoring rules, it extracts and processes equipment operation thresholds, parameter change rates, and anomaly judgment criteria to generate a standardized equipment operation dataset, parameter threshold verification information, equipment status code mapping information, and preliminary data anomaly screening results. By combining the real-time monitoring capabilities of edge computing nodes, the standardized dataset and screening results are verified in a targeted manner. The focus is on tracking the efficiency fluctuations of photovoltaic inverters, the wear of wind turbine gearboxes, the degradation of the sealing performance of water turbines, and the changes in SOC / SOH of energy storage batteries. Parameters that exceed the threshold range are marked with anomaly levels, trend analysis processes are initiated for data with abnormal change rates, and secondary monitoring mechanisms are triggered for data with ambiguous status judgments. Preliminary fault warning information and power output anomaly prompts are generated, including anomaly level classification and monitoring frequency adjustment.

3. The method as described in claim 1, characterized in that, The system processes preliminary fault warnings and power output anomaly alerts. A virtual simulation platform for coordinated operation of hydropower, wind power, and solar power is built using digital twin technology to simulate system output characteristics under different fault conditions. A hierarchical diagnostic strategy and coordinated scheduling plan are designed using a multi-objective optimization algorithm. Power grid safety constraints and equipment operating threshold limits are applied, and target fault diagnosis instructions and power coordination allocation schemes are generated, including: Based on the core characteristics of digital twin technology, such as virtual-real mapping and real-time interaction, preliminary fault warning information, power output anomaly prompts, equipment historical operating data, and environmental benchmark parameters are classified and integrated to generate a basic dataset for twin modeling that includes fault type, anomaly level, and impact range. Based on the simulation accuracy requirements, the functional modules of the virtual simulation platform for coordinated operation of water, wind and solar power are designed, the configuration ratio of equipment simulation model, operating condition simulation engine and output prediction algorithm are clarified, and platform architecture design information is generated; combined with multi-objective optimization algorithm and system safety operation requirements, diagnosis and scheduling rules are set according to the severity of faults and dynamically adjusted according to grid constraints to ensure the coordination of fault handling and power allocation. The twin modeling base dataset, platform architecture design information, and hierarchical scheduling rules are processed to generate target fault diagnosis instructions and power coordination allocation schemes that include model parameters, simulation process, diagnostic criteria, and allocation strategies.

4. The method as described in claim 3, characterized in that, Based on the corresponding adaptive cooperative control algorithm, the target fault diagnosis command and power coordination allocation scheme are processed. Combining real-time grid load demand and weather forecasts, the output ratio of each power generation unit is dynamically adjusted to generate a cooperative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency. This strategy includes: Based on the collaborative control objective, core input information is obtained, and fault handling requirements in the target fault diagnosis command and the output benchmark ratio in the power coordination allocation scheme are extracted. The extracted core information is verified for compliance, confirming the feasibility of fault handling requirements and the rationality of the output benchmark ratio, and generating information verification results. Based on the dynamic adjustment characteristics of the adaptive cooperative control algorithm, the core information of the verification is integrated and analyzed to generate the algorithm input parameter set; By combining real-time grid load demand and short-term meteorological forecast data, the output regulation boundaries of photovoltaic, wind power, hydropower and energy storage units are clarified, and unit regulation constraint information is generated; Based on multi-objective optimization logic, dynamic adjustment rules are set, and the output ratio is optimized in layers according to fault handling priority, power supply stability requirements, and power generation efficiency targets to generate a ratio adjustment scheme. A strategy iteration and update mechanism is set up to adjust the adjustment parameters in real time according to the fluctuation of grid load and changes in weather conditions, and generate a coordinated control strategy that takes into account the accuracy of fault diagnosis, power supply stability and power generation efficiency.

5. The method as described in claim 1, characterized in that, The system processes a coordinated control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency to generate a globally coordinated remote operation and management scheme, including: Multi-dimensional core elements of the collaborative control strategy are extracted, and the output adjustment parameters, fault handling priorities, power supply stability thresholds and power generation efficiency targets of each power generation unit are analyzed. The regional coordination logic and equipment linkage rules in the strategy are identified, and a set of elements to be integrated, including unit control characteristics and system coordination characteristics, is generated. Based on the need for global collaborative management, the set of elements is processed in a coordinated manner. A remote communication protocol adaptation algorithm is used to achieve compatible transmission of cross-regional control commands. A resource optimization configuration model is used to allocate operation and maintenance resources in each region, and global collaborative processing results and evaluation information covering protocol compatibility and resource allocation rationality are generated. Based on the evaluation information, targeted optimizations are performed. Interface debugging mechanisms are used to adjust protocol adaptation deviations, dynamic scheduling algorithms are used to correct resource allocation imbalances, and the matching degree between collaborative logic and device response is re-verified for command interaction anomalies, thereby generating an optimized global collaborative solution. The integrated and optimized global collaboration solution is then finalized by combining the real-time and reliability requirements of remote operation and maintenance, resulting in a global collaborative remote operation and management solution that includes remote communication specifications, resource scheduling procedures, emergency response plans for faults, and a global coordination mechanism.

6. The method as described in claim 5, characterized in that, The system processes preliminary fault warning information and power output anomaly alerts, target fault diagnosis commands, a collaborative control strategy that balances fault diagnosis accuracy and power generation efficiency, and a globally coordinated remote operation management scheme to generate comprehensive evaluation information for the hydro-wind-solar coordinated system, including: Based on a comprehensive evaluation index system, data such as preliminary fault warning information, power output anomaly prompts, target fault diagnosis instructions, collaborative control strategies and remote operation management schemes are integrated to generate a multi-dimensional evaluation basic dataset. An algorithm combining analytic hierarchy process (AHP) and entropy weighting is used to quantify the features of the evaluation dataset and construct a comprehensive evaluation model for the system's operating status. By combining industry standard thresholds with actual operational needs, the weight coefficients and judgment criteria of the evaluation model are iteratively optimized to generate a calibration set of evaluation parameters. Based on the evaluation parameter calibration set, a comprehensive calculation is performed on multi-dimensional index data to generate preliminary evaluation results including fault diagnosis accuracy, power supply stability coefficient, and power generation efficiency value. The preliminary assessment results, quantitative data of indicators, and parameter calibration information are collaboratively verified to generate comprehensive assessment information of the water-wind-solar synergy system, covering system reliability level, fault handling effectiveness, resource allocation rationality, and energy-saving benefit quantification.

7. A multi-protocol integrated water, wind, and solar collaborative control and remote diagnostic device, characterized in that, The device includes: The acquisition module is used to acquire the operating data of each core device in the hydro-wind-solar power generation system and multi-source environmental parameter information; The processing module processes operational data from core equipment in the hydro-wind-solar power generation system, as well as multi-source environmental parameters. It combines edge computing nodes to monitor real-time photovoltaic inverter efficiency, wind turbine gearbox wear, turbine sealing performance, and energy storage battery SOC / SOH, generating preliminary fault warnings and power output anomaly alerts. This preliminary fault warning and power output anomaly alerts are then processed. A virtual simulation platform for coordinated operation of hydro-wind-solar power generation is built using digital twin technology to simulate system output characteristics under different fault conditions. Multi-objective optimization algorithms are used to design hierarchical diagnostic strategies and coordinated scheduling plans, imposing grid safety constraints and equipment operating threshold limits to generate target fault diagnosis commands and power coordination allocation. The solution involves processing the target fault diagnosis command and power coordination allocation scheme based on the corresponding adaptive cooperative control algorithm, dynamically adjusting the output ratio of each power generation unit in conjunction with real-time grid load demand and weather forecasts, and generating a cooperative control strategy that balances fault diagnosis accuracy, power supply stability, and power generation efficiency. This cooperative control strategy is then processed to generate a globally coordinated remote operation management scheme. Finally, preliminary fault warning information and power output anomaly alerts, target fault diagnosis commands, the cooperative control strategy balancing fault diagnosis accuracy and power generation efficiency, and the globally coordinated remote operation management scheme are processed to generate comprehensive evaluation information for the hydro-wind-solar coordinated system.

8. An electronic device, characterized in that, include: First processor; and memory for storing executable instructions of the first processor; The first processor is configured to execute the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the second processor, it implements the integrated multi-protocol water-wind-solar collaborative control and remote diagnostic method according to any one of claims 1 to 6.

Images