Photovoltaic power station global intelligent cooperative control system and method based on digital twinning

Abstract

The invention relates to the field of photovoltaic power station control systems, in particular to a photovoltaic power station global intelligent cooperative control system and method based on digital twinning. The technical problem to be solved by the invention is to provide the global intelligent cooperative control system and method based on the digital twin photovoltaic power station, which can map the operation state of a physical power station in real time and realize panoramic insight and intelligent cooperative control of the power station. The invention discloses a photovoltaic power station global intelligent cooperative control system and method based on digital twinning, and the system comprises a data collection and perception layer which is disposed in a physical space of a photovoltaic power station, and is used for collecting the global operation data and environmental data of the photovoltaic power station in real time; and the digital twinborn body construction and simulation layer is in communication connection with the data acquisition and perception layer and is used for constructing and updating a digital twinborn model of the photovoltaic power station based on the acquired data. The method achieves the effects of mapping the operation state of the physical power station in real time, and achieving the panoramic insight and intelligent cooperative control of the power station.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power plant control systems, and in particular to a fully intelligent collaborative control system and method for photovoltaic power plants based on digital twins. Background Technology

[0002] With the accelerated advancement of energy transition, photovoltaic (PV) power generation, as an important component of clean energy, has seen continuous expansion in installed capacity and power plant scale. However, the operating efficiency and power generation benefits of PV power plants are strongly influenced by environmental factors such as sunlight and temperature, and the number of devices within the plant is large, widely distributed, and their operating characteristics are complex. Traditional PV power plant monitoring and control systems typically focus on the independent control of local equipment or single processes, lacking the ability to uniformly perceive and collaboratively optimize the overall operating status of the power plant. Existing systems mostly use empirical models or simple physical models based on historical data for power prediction and control, which are difficult to accurately reflect the dynamic operating characteristics of the power plant and equipment performance degradation, resulting in suboptimal power generation efficiency and delayed equipment fault warnings and maintenance responses. Furthermore, with the increasing demands of the power grid for the dispatch of new energy power plants, PV power plants need to have the ability to quickly and accurately respond to power regulation commands from the grid. Existing control strategies often struggle to effectively balance multiple objectives such as power generation revenue, equipment lifespan, and grid friendliness, and have not yet formed a comprehensive collaborative control mechanism that integrates real-time data, high-precision modeling, and intelligent decision-making. Therefore, there is an urgent need to develop a comprehensive intelligent collaborative control system and method for PV power plants based on digital twins that can map the physical operating status of the power plant in real time and achieve panoramic insight and intelligent collaborative control of the power plant. Summary of the Invention

[0003] In order to overcome the shortcomings of existing systems that mostly use empirical models or simple physical models based on historical data for power prediction and control, which are difficult to accurately reflect the dynamic operating characteristics of the power plant and the performance degradation of the equipment, resulting in suboptimal power generation efficiency and lagging equipment fault warning and maintenance response, the present invention aims to provide a full-domain intelligent collaborative control system and method for photovoltaic power plants based on digital twins that can map the physical operating status of the power plant in real time and realize panoramic insight and intelligent collaborative control of the power plant.

[0004] This invention is achieved through the following specific technical means: A digital twin-based intelligent collaborative control system for the entire photovoltaic power station includes: The data acquisition and sensing layer is deployed in the physical space of the photovoltaic power station to collect real-time operational and environmental data across the entire photovoltaic power station area. The digital twin construction and simulation layer is communicatively connected to the data acquisition and perception layer, and is used to construct and update the digital twin model of the photovoltaic power station based on the acquired data; The global intelligent collaborative control layer interacts with the digital twin construction and simulation layer to perform simulation, prediction and optimization analysis based on the digital twin model, and generate a global collaborative control strategy. The control command execution layer is connected to the global intelligent collaborative control layer and each execution device in the physical space of the photovoltaic power station, and is used to convert the collaborative control strategy into specific control commands and issue them for execution; The digital twin construction and simulation layer includes a model fusion and update unit, which is used to fuse a physical model based on physical mechanisms with a data-driven model trained on historical data, and to perform dynamic calibration using real-time data. The global intelligent collaborative control layer includes a collaborative decision center, which is used to weigh the outputs of power generation optimization, equipment health management and grid dispatch response based on a preset multi-objective optimization function, and generate the global collaborative control strategy.

[0005] Furthermore, the data acquisition and sensing layer covers the operational data of photovoltaic module arrays, inverters, combiner boxes, booster stations, and meteorological monitoring units.

[0006] Furthermore, the digital twin construction and simulation layer also includes: The physical model unit is used to build high-fidelity equipment models based on the physical characteristics, electrical topology, and environmental parameters of photovoltaic modules. The data-driven model unit is used to train power plant performance prediction and fault diagnosis models based on historical operating data and through machine learning algorithms.

[0007] Furthermore, the global intelligent collaborative control layer also includes: The power generation optimization module is used to simulate the maximum power point tracking strategy of each photovoltaic string under different environmental conditions in the digital twin model and to perform global power optimization. The equipment health management module is used to analyze the performance degradation trend of key equipment based on the digital twin model, predict failure risks, and generate early warning and maintenance strategies. The power grid dispatch response module is used to receive power grid dispatch instructions, simulate multiple control schemes in the digital twin model, and select the optimal scheme to achieve fast and accurate control of active / reactive power.

[0008] Furthermore, the control instruction execution layer includes: The instruction allocation unit is used to parse the global collaborative control strategy and allocate it to the corresponding execution device controller; The safety verification unit is used to verify whether the instruction is within the safe operating threshold range of the device before it is issued. The feedback closed-loop unit is used to collect the actual effect data after the instruction is executed and feed it back to the digital twin construction and simulation layer to form closed-loop control.

[0009] Furthermore, it also includes a cloud-edge collaborative computing platform to provide computing support for the construction and simulation layer of the digital twin and the global intelligent collaborative control layer; the cloud-edge collaborative computing platform includes a cloud-based big data center for non-real-time big data analysis and long-term model training, and edge computing nodes for handling local control and simulation with high real-time requirements.

[0010] A method for intelligent collaborative control of the entire photovoltaic power plant based on digital twins, comprising: S1: Real-time acquisition of diverse operational and environmental data of the physical space of the photovoltaic power station; S2: Based on the data, construct and update in real time a digital twin model of a photovoltaic power station that integrates physical mechanisms and data-driven models; S3: Perform global simulation and multi-objective optimization analysis based on the digital twin model, wherein the multi-objective optimization integrates at least three dimensions: power generation revenue, equipment lifespan, and grid friendliness, in order to generate a global collaborative control strategy; S4: Distribute the collaborative control strategy to the corresponding execution equipment of the physical power station; S5: Based on the feedback data after the instruction is executed, the digital twin model and control strategy are iteratively optimized.

[0011] Furthermore, the construction and real-time updating of the digital twin model in step S2 specifically includes: A physical mechanism model is established based on the equipment parameters and topology of photovoltaic power plants; Based on historical operational data, train a data-driven performance prediction and fault diagnosis model; Data assimilation technology is used to fuse real-time collected data with the physical mechanism model and the data-driven model, and to dynamically correct the model parameters.

[0012] Furthermore, the generation of the global collaborative control strategy in step S3 specifically includes: In response to power grid dispatch instructions or the detection of sudden environmental changes, multiple candidate control schemes are generated in the digital twin model; Perform rapid simulations for each candidate control scheme to predict its power generation, equipment stress, and grid connection performance. The simulation results are evaluated based on the multi-objective optimization function, and the candidate scheme with the best overall performance is selected as the global cooperative control strategy.

[0013] Compared with the prior art, the present invention has the following beneficial effects: This invention achieves real-time mapping of the physical power plant's operating status, enabling panoramic insight and intelligent collaborative control of the power plant. Attached Figure Description

[0014] Figure 1 This is a system framework diagram of the present invention. Detailed Implementation

[0015] The present invention will be further described below with reference to the accompanying drawings: Example

[0016] A digital twin-based intelligent collaborative control system for the entire photovoltaic power station, such as... Figure 1 As shown, it includes: The data acquisition and sensing layer is deployed in the physical space of the photovoltaic power station to collect real-time operational and environmental data across the entire photovoltaic power station area. The digital twin construction and simulation layer is communicatively connected to the data acquisition and perception layer, and is used to construct and update the digital twin model of the photovoltaic power station based on the acquired data; The global intelligent collaborative control layer interacts with the digital twin construction and simulation layer to perform simulation, prediction and optimization analysis based on the digital twin model, and generate a global collaborative control strategy. The control command execution layer is connected to the global intelligent collaborative control layer and each execution device in the physical space of the photovoltaic power station, and is used to convert the collaborative control strategy into specific control commands and issue them for execution; The digital twin construction and simulation layer includes a model fusion and update unit, which is used to fuse a physical model based on physical mechanisms with a data-driven model trained on historical data, and to perform dynamic calibration using real-time data. The global intelligent collaborative control layer includes a collaborative decision-making center, which is used to weigh the outputs of power generation optimization, equipment health management and grid dispatch response based on a preset multi-objective optimization function, and generate the global collaborative control strategy. The digital twin construction and simulation layer also includes: a physical model unit, used to construct a high-fidelity equipment model based on the physical characteristics, electrical topology and environmental parameters of photovoltaic modules; and a data-driven model unit, used to train a power plant performance prediction and fault diagnosis model based on historical operating data and through machine learning algorithms. The global intelligent collaborative control layer also includes: a power generation optimization module, used to simulate the maximum power point tracking strategy of each photovoltaic string under different environmental conditions in the digital twin model, and to perform global power optimization; an equipment health management module, used to analyze the performance degradation trend of key equipment based on the digital twin model, predict fault risks, and generate early warning and maintenance strategies; and a grid dispatch response module, used to receive grid dispatch instructions, simulate multiple control schemes in the digital twin model, and select the optimal scheme to achieve rapid and accurate control of active / reactive power.

[0017] The control command execution layer includes: a command allocation unit, used to parse and allocate the global collaborative control strategy to the corresponding execution device controller; a security verification unit, used to verify whether the command is within the safe operation threshold range of the device before it is issued; and a feedback closed-loop unit, used to collect the actual effect data after the command is executed and feed it back to the digital twin construction and simulation layer to form closed-loop control. A method for intelligent collaborative control of the entire photovoltaic power plant based on digital twins, comprising: S1: Real-time acquisition of diverse operational and environmental data of the physical space of the photovoltaic power station; S2: Based on the data, construct and update in real time a digital twin model of a photovoltaic power station that integrates physical mechanisms and data-driven models; S3: Perform global simulation and multi-objective optimization analysis based on the digital twin model, wherein the multi-objective optimization integrates at least three dimensions: power generation revenue, equipment lifespan, and grid friendliness, in order to generate a global collaborative control strategy; S4: Distribute the collaborative control strategy to the corresponding execution equipment of the physical power station; S5: Based on the feedback data after the instruction is executed, the digital twin model and control strategy are iteratively optimized.

[0018] Working principle: First, the data acquisition and perception layer, as the information entry point, is deployed in the physical space of the photovoltaic power station to collect real-time operating data (such as voltage, current, power, and equipment temperature) from photovoltaic module arrays, inverters, combiner boxes, and booster stations, as well as environmental data (such as light intensity, wind speed, and temperature) from meteorological monitoring units, providing real-time, full-domain data sources for subsequent digital twin modeling. Secondly, after receiving the collected data, the digital twin construction and simulation layer completes the construction of the digital twin space through dual-model collaboration: on the one hand, the physical model unit establishes a high-fidelity equipment model based on the physical characteristics and electrical topology of the equipment; on the other hand, the data-driven model unit uses historical operating data to train performance prediction and fault diagnosis models through machine learning; finally, the model fusion and update unit uses data assimilation technology to fuse the dual models with the real-time collected data, dynamically calibrate the model parameters, and realize the real-time update of the photovoltaic power station digital twin model, ensuring that the model is highly consistent with the physical power station state; in this process, the cloud-edge collaborative computing platform provides computing power support, in which edge computing nodes handle real-time modeling and simulation tasks, and the cloud big data center is responsible for historical data storage, non-real-time big data analysis, and long-term model training and optimization; Next, the global intelligent collaborative control layer carries out core management and control based on the updated digital twin model: the power generation optimization module simulates the maximum power point tracking strategy of photovoltaic strings under different environments to maximize global power; the equipment health management module analyzes the performance degradation trend of equipment, predicts fault risks, and generates maintenance strategies; after receiving grid commands, the grid dispatch response module simulates multiple control schemes in the digital twin model to predict the power generation, equipment stress, and grid connection indicators of each scheme; finally, the collaborative decision-making center, based on the preset multi-objective optimization function (comprehensive power generation revenue, equipment lifespan, and grid friendliness), weighs the outputs of each module and generates a global collaborative control strategy. Finally, the control command execution layer takes over the control strategy. First, the command allocation unit parses the strategy and allocates it to the corresponding execution device controller. Then, the safety verification unit verifies whether the command is within the safe operation threshold of the device to ensure execution safety. After the command is issued and executed, the feedback closed-loop unit collects the actual operation data of the device and sends it back to the digital twin construction and simulation layer. On the one hand, this is used to further calibrate the digital twin model, and on the other hand, it provides a basis for the full-domain intelligent collaborative control layer to optimize the control strategy, thereby improving the operating efficiency and control accuracy of the photovoltaic power station.

[0019] Although this disclosure has been described in detail with reference to exemplary embodiments, it is not limited thereto, and it will be apparent to those skilled in the art that various modifications and changes may be made thereto without departing from the scope of this disclosure.

Claims

1. A fully intelligent collaborative control system for photovoltaic power plants based on digital twins, characterized in that, Including: The data acquisition and sensing layer is deployed in the physical space of the photovoltaic power station to collect real-time operational and environmental data across the entire photovoltaic power station area. The digital twin construction and simulation layer is communicatively connected to the data acquisition and perception layer, and is used to construct and update the digital twin model of the photovoltaic power station based on the acquired data; The global intelligent collaborative control layer interacts with the digital twin construction and simulation layer to perform simulation, prediction and optimization analysis based on the digital twin model, and generate a global collaborative control strategy. The control command execution layer is connected to the global intelligent collaborative control layer and each execution device in the physical space of the photovoltaic power station, and is used to convert the collaborative control strategy into specific control commands and issue them for execution; The digital twin construction and simulation layer includes a model fusion and update unit, which is used to fuse a physical model based on physical mechanisms with a data-driven model trained on historical data, and to perform dynamic calibration using real-time data. The global intelligent collaborative control layer includes a collaborative decision center, which is used to weigh the outputs of power generation optimization, equipment health management and grid dispatch response based on a preset multi-objective optimization function, and generate the global collaborative control strategy.

2. The photovoltaic power station intelligent collaborative control system based on digital twin as described in claim 1, characterized in that, The data acquisition and sensing layer covers the operational data of photovoltaic module arrays, inverters, combiner boxes, booster stations, and meteorological monitoring units.

3. The photovoltaic power station intelligent collaborative control system based on digital twin as described in claim 1, characterized in that, The digital twin construction and simulation layer also includes: The physical model unit is used to build high-fidelity equipment models based on the physical characteristics, electrical topology, and environmental parameters of photovoltaic modules. The data-driven model unit is used to train power plant performance prediction and fault diagnosis models based on historical operating data and through machine learning algorithms.

4. The photovoltaic power station intelligent collaborative control system based on digital twin as described in claim 1, characterized in that, The global intelligent collaborative control layer also includes: The power generation optimization module is used to simulate the maximum power point tracking strategy of each photovoltaic string under different environmental conditions in the digital twin model and to perform global power optimization. The equipment health management module is used to analyze the performance degradation trend of key equipment based on the digital twin model, predict failure risks, and generate early warning and maintenance strategies. The power grid dispatch response module is used to receive power grid dispatch instructions, simulate multiple control schemes in the digital twin model, and select the optimal scheme to achieve fast and accurate control of active / reactive power.

5. The photovoltaic power station intelligent collaborative control system based on digital twin as described in claim 1, characterized in that, The control instruction execution layer includes: The instruction allocation unit is used to parse the global collaborative control strategy and allocate it to the corresponding execution device controller; The safety verification unit is used to verify whether the instruction is within the safe operating threshold range of the device before it is issued. The feedback closed-loop unit is used to collect the actual effect data after the instruction is executed and feed it back to the digital twin construction and simulation layer to form closed-loop control.

6. The photovoltaic power station intelligent collaborative control system based on digital twin as described in claim 1, characterized in that, It also includes a cloud-edge collaborative computing platform, which provides computing support for the construction and simulation layer of the digital twin and the global intelligent collaborative control layer; the cloud-edge collaborative computing platform includes a cloud-based big data center for non-real-time big data analysis and long-term model training, and edge computing nodes for handling local control and simulation with high real-time requirements.

7. A method for intelligent collaborative control of a photovoltaic power station based on digital twins, characterized in that, include: S1: Real-time acquisition of diverse operational and environmental data of the physical space of the photovoltaic power station; S2: Based on the data, construct and update in real time a digital twin model of a photovoltaic power station that integrates physical mechanisms and data-driven models; S3: Perform global simulation and multi-objective optimization analysis based on the digital twin model, wherein the multi-objective optimization integrates at least three dimensions: power generation revenue, equipment lifespan, and grid friendliness, in order to generate a global collaborative control strategy; S4: Distribute the collaborative control strategy to the corresponding execution equipment of the physical power station; S5: Based on the feedback data after the instruction is executed, the digital twin model and control strategy are iteratively optimized.

8. The method for intelligent collaborative control of a photovoltaic power station based on digital twins according to claim 7, characterized in that, The specific steps in step S2, including constructing and updating the digital twin model in real time, include: A physical mechanism model is established based on the equipment parameters and topology of photovoltaic power plants; Based on historical operational data, train a data-driven performance prediction and fault diagnosis model; Data assimilation technology is used to fuse real-time collected data with the physical mechanism model and the data-driven model, and to dynamically correct the model parameters.

9. The method for intelligent collaborative control of a photovoltaic power station based on digital twins according to claim 7, characterized in that, The specific steps in step S3 to generate the global collaborative control strategy include: In response to power grid dispatch instructions or the detection of sudden environmental changes, multiple candidate control schemes are generated in the digital twin model; Perform rapid simulations for each candidate control scheme to predict its power generation, equipment stress, and grid connection performance. The simulation results are evaluated based on the multi-objective optimization function, and the candidate scheme with the best overall performance is selected as the global cooperative control strategy.

Images