New energy station simulation deduction method and system, medium and processor

Abstract

The invention discloses a new energy station simulation deduction method and system, a medium and a processor, and relates to the technical field of new energy power station operation optimization, and the method comprises the steps: obtaining the operation state data and resource prediction data of a new energy station; based on the operation state data, synchronously constructing a station digital twinborn model; in the station digital twinborn model, loading resource prediction data as a boundary condition, and paralleling different candidate operation strategies; driving the digital twin model of the field station to carry out advanced simulation deduction, respectively simulating operation processes under the control of different candidate operation strategies in the future preset time period, and generating multiple groups of rehearsal result data corresponding to each candidate strategy; and on the basis of a predefined optimization objective function, performing online evaluation and comparison on the multiple groups of rehearsal result data, and outputting an optimal candidate operation strategy as strategy recommendation. By rehearsing the future in the virtual space, results caused by different strategies can be predicted in advance, and an automatic control system makes an optimal decision.

Description

Technical Field

[0001] This invention relates to the field of new energy power plant operation optimization technology, and in particular to a new energy power plant simulation and deduction method, system, medium and processor. Background Technology

[0002] The new energy industry is currently experiencing large-scale development, with wind power and photovoltaic power plants gradually becoming the core force in energy supply. However, the output of new energy sources is highly volatile and intermittent due to natural conditions, and large-scale grid connection poses challenges to the stable operation of the power grid. At the same time, under the background of energy transition, new energy power plants need to balance power generation efficiency, safe operation, and grid dispatch adaptability. Traditional experience-based operation strategies can no longer meet the needs of refined management, and there is an urgent need to optimize operation decisions through simulation and simulation technology.

[0003] Existing simulation technologies for new energy power plants mostly use single-dimensional simulation models, which make it difficult to synchronously map the dynamic coupling relationship between the real-time status of equipment and the operation strategy. Furthermore, the boundary conditions are fixed during the simulation process, resulting in a large deviation between the simulation results and the actual operation. This leads to low extrapolation efficiency, makes it impossible to achieve optimal decision output for multiple strategies in the future, and makes it difficult to support the advanced optimization and adjustment of the power plant operation strategy. Summary of the Invention

[0004] To address the problem that existing technologies for simulating renewable energy power plants cannot achieve optimal decision-making output for multiple strategies in the future, this invention provides a method, system, medium, and processor for simulating renewable energy power plants. By rehearsing the future in virtual space, it can predict the possible outcomes of different strategies in advance, enabling the automatic control system to make the optimal decision. The specific technical solution is as follows: In a first aspect, the present invention provides a simulation and deduction method for new energy power plants, comprising: Acquire operational status data and resource forecast data for future preset time periods from new energy power plants; Based on the operational status data, a digital twin model of the site is constructed synchronously. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operational strategy. In the digital twin model of the site, the resource prediction data is loaded as a boundary condition, and at least two different candidate operation strategies are injected in parallel. The digital twin model of the station is driven to perform advanced simulation and deduction, respectively simulating the operation process under the control of different candidate operation strategies within the future preset time period, and generating multiple sets of pre-simulation result data corresponding to each candidate strategy; Based on a predefined optimization objective function, the multiple sets of pre-simulation result data are evaluated and compared online, and the optimal candidate running strategy is output as a strategy recommendation.

[0005] Preferably, the operating status data includes at least the real-time output power, switching status, available capacity, and temperature data of key components of each power generation unit.

[0006] Preferably, the step of synchronously constructing a digital twin model of the site based on the operational status data includes: The available capacity is set as the upper limit of the simulated power of the corresponding power generation unit in the performance simulation layer, and the temperature of the key component is used as the input parameter of the loss calculation module in the performance simulation layer.

[0007] Preferably, the synchronous construction of the digital twin model of the site includes: In a simulation server independent of the physical site control system, the simulated on / off status of each power generation unit is initialized based on the switch status in the operating status data; Based on the real-time output power and resource prediction data, the internal intermediate variables in the performance simulation layer are initialized so that the simulation start state of the digital twin model of the power station matches the current actual operating state of the physical power station.

[0008] Preferably, the parallel injection includes at least two different candidate execution strategies: First strategy: An optimized operation strategy based on the resource prediction data, with the goal of maximizing the power generation of the entire station; Second strategy: A tracking operation strategy that receives and tracks preset power commands from external systems; The first strategy and the second strategy are executed synchronously under the same initial state in the advanced simulation.

[0009] Preferably, a simulation and deduction method for new energy power stations further includes: During the advanced simulation process, the simulation data under any candidate operation strategy is monitored in real time to see if it triggers the preset alarm conditions; if it is triggered, the simulation is immediately interrupted and an early warning report is generated, including the alarm strategy, alarm time and alarm content.

[0010] Preferably, the objective function is calculated as follows: Based on preset multi-dimensional weighting coefficients, multiple key performance indicators in the multiple sets of pre-simulation result data are weighted and calculated to generate a comprehensive score corresponding to each candidate running strategy.

[0011] Secondly, the present invention also provides a simulation and deduction system for new energy power plants, which applies the aforementioned method and includes: The data acquisition unit is used to acquire the operating status data of new energy power plants and the resource prediction data for a future preset period. A digital twin engine is used to synchronously construct a digital twin model of the site based on the operational status data. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operational strategy. The strategy management unit is used to load the resource prediction data as boundary conditions into the digital twin model of the site and inject at least two different candidate operation strategies in parallel. The simulation and deduction unit is used to drive the digital twin model of the site to perform advanced simulation and deduction, respectively simulating the operation process under the control of different candidate operation strategies within the future preset time period, and generating multiple sets of pre-simulation result data corresponding to each candidate strategy; The evaluation and decision-making unit is used to evaluate and compare the multiple sets of pre-simulation result data online based on a predefined optimization objective function, and output the optimal candidate running strategy as a strategy recommendation.

[0012] Thirdly, the present invention also provides a computer-readable storage medium comprising a stored program, wherein, when the program is executed, the device containing the computer-readable storage medium performs the steps of the aforementioned simulation and deduction method for a new energy power station.

[0013] Fourthly, the present invention also provides a processor for running a program, wherein the program executes the aforementioned simulation and deduction method for a new energy power station.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a simulation and extrapolation method for new energy power plants. By utilizing digital twins and real-time data, it allows operators to simulate the entire execution process of different strategies over the next few hours, seeing the specific results of each strategy, such as power generation, equipment load, and command tracking deviations. This enables operators to select strategies with higher expected returns or greater safety based on clear predictive data, thereby improving the initiative in daily operations and reducing power losses or equipment damage caused by blind decision-making. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of a simulation and deduction method for a new energy power station according to the present invention.

[0017] Figure 2This is a schematic diagram of a new energy power station simulation system according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0020] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0021] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0022] Please refer to the following examples. Figure 1 and Figure 2 .

[0023] This invention provides a simulation and deduction method for new energy power stations, the execution entity of which is a simulation and deduction server deployed at the power station or regional dispatch center, and the method includes: Step S1: Obtain the operating status data of the new energy power station and the resource prediction data for the future preset time period; Operational status data is directly obtained from real-time or historical databases of the renewable energy power plant's Supervisory Control and Data Acquisition (SCADA) system, power prediction system, and equipment condition monitoring system. The data includes electrical status data, equipment status data, and environmental status data. The acquired data undergoes cleaning, verification, and time alignment to remove outliers and unify timestamps to the same baseline.

[0024] In one specific embodiment, the operating status data includes at least the real-time output power, switching status, available capacity, and temperature data of key components of each power generation unit.

[0025] Real-time output power refers to the actual active and reactive power output of a single wind turbine, photovoltaic string, or inverter power generation unit at the current moment. During model initialization, the output power of the simulation model must match the actual power value at this moment, so that the starting point of the deduction is consistent with the physical world.

[0026] Switch status refers to the on / off state of circuit breakers, disconnectors, DC switches of photovoltaic arrays, combiner box switches, etc., of generator sets. This determines which devices should be included in the current operational topology network in the digital twin model. For example, a wind turbine disconnected for maintenance should have its corresponding unit in the simulation model set to the off state.

[0027] Available capacity is a dynamically changing parameter that reflects the maximum permissible or maximum power output of a device under current environmental conditions and its own state. For wind turbines, it may be limited by wind speed and derating due to ambient temperature; for photovoltaics, it may be limited by irradiance and module temperature; and for energy storage, it is limited by the charge / discharge power output at the current state of charge (SOC). In the performance simulation layer, available capacity serves as the upper limit constraint on the power output of the power generation unit during the simulation process, and is a key parameter for determining the feasibility of the simulation results.

[0028] Temperature data for key components is crucial for performance simulation. Examples include the gearbox bearing temperature, generator winding temperature, and IGBT junction temperature of a wind turbine; and the radiator temperature and transformer oil temperature of a photovoltaic inverter. Temperature data directly correlates with the equipment's operating efficiency, losses, and aging rate. In the digital twin model, this temperature data is input into the loss calculation module and the life assessment module. For example, higher bearing temperatures may indicate higher mechanical friction losses, resulting in a larger loss value being deducted when calculating the actual net output power of the wind turbine under the current strategy in the simulation, making the simulation results closer to the equipment's performance under real operating conditions.

[0029] Resource forecasting data is acquired by accessing commercial or self-built high-precision numerical weather prediction (NWP) services, or by power forecasting data issued by higher-level dispatching agencies. This covers spatiotemporal series data for a predetermined future period, including wind resource forecasts, solar resource forecasts, and environmental forecasts. The acquired gridded forecasting data is then matched to the specific location of each power generation unit within the power station using spatial interpolation or downscaling methods, forming the driving data sequence for each unit.

[0030] Step S2: Based on the operating status data, synchronously construct a digital twin model of the site. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operating strategy. The performance simulation layer parameterizes and establishes a mathematical model for each physical power generation device and its associated electrical connections within the power station. Using the real-time device status data obtained in step S1, the model parameters are dynamically updated, transforming the model from a design parameter model to a current state model. For example, the available capacity value reported by SCADA is set as the maximum output limit parameter of the corresponding device's simulation model. The real-time measured component temperature is used as input to the loss calculation submodule in the simulation model to dynamically calculate efficiency and losses under the current operating conditions. Based on the real-time SOC and temperature of the energy storage battery, the internal resistance, open-circuit voltage, and other equivalent circuit parameters in its simulation model are adjusted. This ensures that, given inputs, the output characteristics of the performance simulation layer can reflect the actual behavior of the device under its current health state and operating conditions.

[0031] The instantiation of the strategy simulation layer simulates the control system logic at the station level or unit level, i.e., the currently effective operating strategy.

[0032] The complete logic and parameters of the currently executing operating strategy are read from the power station's energy management system (EMS) or controller. For example, is the current mode maximum power point tracking (MPPT), constant power control, or frequency modulation? The control algorithm of this strategy is then completely copied to the corresponding control module in the strategy simulation layer. This ensures that the control behavior of the digital twin model at the start of the simulation is completely consistent with that of the physical power station.

[0033] Step S3: In the digital twin model of the site, load the resource prediction data as boundary conditions and inject at least two different candidate operation strategies in parallel; In practice, the future resource prediction data sequence obtained in step S1 is formally input into the digital twin model of the power station constructed in step S2. This data serves as an external driving source for the simulation model, replacing real-time measurements during the simulation process to drive the power generation unit models in the performance simulation layer to calculate theoretical power generation. For example, at each simulation step, the predicted wind speed sequence is input into the wind turbine aerodynamic model, and the predicted irradiance and temperature are input into the photovoltaic cell model.

[0034] Candidate strategies can come from a pre-defined strategy library, instructions issued by external systems, or new strategies generated by real-time optimization algorithms. In the simulation server, an independent strategy simulation layer instance is created for each candidate strategy to be evaluated. Each instance branches off from the current instantiated state of the actual strategy but loads different control logic.

[0035] The typical candidate strategies are selected as follows: Strategy A: An optimization strategy that aims to maximize the expected electricity revenue of all stations during the simulation period, taking into account electricity prices and equipment loss costs.

[0036] Strategy B: A power control strategy aimed at strictly tracking the future power plan curve issued by the superior dispatching agency.

[0037] Strategy C: A strategy that prioritizes reducing cumulative fatigue in key equipment components and controlling operating temperature within a safe range.

[0038] All candidate strategies begin preparation for execution in parallel and independently at the same time point, based on the same resource prediction data and the same initialized performance simulation model.

[0039] Step S4: Drive the digital twin model of the station to perform advanced simulation and deduction, simulate the operation process under different candidate operation strategies within the future preset time period, and generate multiple sets of pre-simulation result data corresponding to each candidate strategy; In practice, a high-performance power system and dynamic system simulation kernel is used to drive the entire digital twin model of the power station. The simulation server starts multiple parallel simulation calculation processes or threads, each process corresponding to a combination of a performance simulation layer and a policy simulation layer for a specific candidate policy.

[0040] Within each simulation step, the process is as follows: The strategy simulation layer calculates the control commands for each virtual device based on the current simulated system state and its control objectives. The performance simulation layer receives control commands and current resource prediction data, and calculates the physical response of each virtual device under the command and the electrical status of the entire station. The new system state is fed back to the policy simulation layer as input for the next simulation step, forming a closed loop.

[0041] Throughout the simulation over the entire predetermined time period, full simulation process data corresponding to each candidate strategy is continuously recorded. The result dataset typically includes full-field and unit-level power curves, key equipment state curves, performance indicators, control indicators, and safety indicators. After the simulation ends at the predetermined time period, a structured pre-simulation result data package is generated for each candidate strategy.

[0042] Step S5: Based on the predefined optimization objective function, perform online evaluation and comparison of the multiple sets of pre-simulation result data, and output the optimal candidate running strategy as a strategy recommendation.

[0043] Specifically, the objective function is calculated as follows: Based on preset multi-dimensional weighting coefficients, multiple key performance indicators in the multiple sets of pre-simulation result data are weighted and calculated to generate a comprehensive score corresponding to each candidate running strategy.

[0044] In one specific embodiment, let's assume that... The candidate strategies were deduced. For the first... One strategy is to extract from the pre-simulation result data. Key performance indicators (KPIs) constitute a vector. .

[0045] For efficiency-related indicators, such as total power generation : For cost-related metrics, such as average tracking error : After normalization, all .

[0046] Preset weight coefficient vector for each indicator ,satisfy , Then the first Overall score of each strategy for: Finally, the optimal strategy Determined by the following formula: System output strategy As a recommendation.

[0047] These objectives are unified into a comparable value through a comprehensive scoring formula with configurable weights. The operations administrator can easily adjust the weighting coefficients based on the company's current management direction. The system will then automatically rank and recommend all proposed strategies based on the new direction.

[0048] This invention provides a simulation and extrapolation method for new energy power plants. By utilizing digital twins and real-time data, it allows operators to simulate the entire execution process of different strategies over the next few hours, seeing the specific results of each strategy, such as power generation, equipment load, and command tracking deviations. This enables operators to select strategies with higher expected returns or greater safety based on clear predictive data, thereby improving the initiative in daily operations and reducing power losses or equipment damage caused by blind decision-making.

[0049] Specifically, in a preferred embodiment, the step of synchronously constructing a digital twin model of the site based on the operational status data includes: The available capacity is set as the upper limit of the simulated power of the corresponding power generation unit in the performance simulation layer, and the temperature of the key component is used as the input parameter of the loss calculation module in the performance simulation layer.

[0050] Set up a power generation unit At any moment The real-time available capacity is This value is reported by the monitoring system. It represents the maximum allowable output considering the current environment and equipment status. In the performance simulation layer of the digital twin model, this is the upper limit of the simulated power of this unit at the start of the simulation. Set as: This constraint applies throughout the subsequent simulation period. , The effect persists within [+T], meaning that at any simulation time τ in the deduction, we have: in, Let be the simulated output power of element i at simulation time τ.

[0051] Let the critical component j of power generation unit i be at time... The real-time temperature is In the loss calculation module of the performance simulation layer, a temperature-loss mapping function for this component is preset. This function can be derived by fitting experimental data or a physical model. In each calculation step k of the simulation, the theoretical power generation is first calculated based on resource prediction data. Then, using real-time temperature or a loss coefficient derived from temperature, the additional loss for that step size is calculated. : Alternatively, temperature can be used as a state variable in the dynamic thermal circuit model: The available capacity is set as the upper limit of the simulated power. In each sub-model of a power generation unit in the performance simulation layer, there is a module for calculating its maximum possible output power. In traditional simulations, this upper limit is usually a fixed nameplate capacity. In this embodiment, it is designed to receive and respond to real-time incoming available capacity data. For example, for a wind turbine with a rated power of 2.5MW, if its available capacity is 2.2MW due to derating caused by high temperatures, the upper limit parameter of the wind turbine in the simulation model is immediately updated to 2.2MW. In subsequent advanced simulations, regardless of the control strategy applied, the simulated output power of the wind turbine will not exceed this dynamic upper limit. This ensures that the simulation results strictly conform to the physical limits of the equipment under current objective conditions, avoiding the simulation of unrealistic high-power scenarios.

[0052] The temperature of key components is used as an input parameter for the loss calculation module. The loss calculation module in the performance simulation layer is crucial to the simulation accuracy. By using typical values ​​or empirical formulas, it is upgraded to a dynamic calculation model based on real-time temperature.

[0053] Traditional optimization simulations often assume that equipment is always operating under rated or standard conditions, neglecting the hard constraints of derating or high-temperature equipment conditions on actual operating boundaries and the soft impact on efficiency. This can lead to optimization strategies failing to achieve the expected results in actual implementation, or even causing equipment overload. In this embodiment, by dynamically setting power limits and using temperature-based loss calculations, the simulation model can faithfully reflect the real-time capabilities and states of the physical equipment. Simultaneously, temperature-based loss calculations make predictions of power generation and efficiency more accurate, effectively avoiding decision-making biases caused by model distortion.

[0054] Specifically, the synchronous construction of the digital twin model of the site includes: In a simulation server independent of the physical site control system, the simulated on / off status of each power generation unit is initialized based on the switch status in the operating status data; Based on the real-time output power and resource prediction data, the internal intermediate variables in the performance simulation layer are initialized so that the simulation start state of the digital twin model of the power station matches the current actual operating state of the physical power station.

[0055] The construction, loading, and operation of digital twin models are carried out in a dedicated computing environment that is physically or logically isolated from the actual control system of the site, within a simulation server independent of the physical site control system. This architecture completely avoids the risk of simulation experiments interfering with or causing malfunctions in the actual production system.

[0056] Let the initial conditions be ( )= ( Total loss This is the sum of losses from all components. Finally, the simulated net output power is: To match the initial state of the simulation with the physical station, the internal state variable xi of the model needs to be calibrated. (It is known that...) Measured output power at time and measured resource data Solve the following equations or optimization problems to obtain the initialized state variables. : in, Indicates that in a given resource and state variables Below, the output power calculation function for the performance simulation layer. After calibration, set... ( )= .

[0057] Simulations are performed on a dedicated server, ensuring that any calculation errors or extreme tests during the simulation process do not directly affect the actual control of the field equipment. Furthermore, the initialization process ensures that the simulation does not begin from a hypothetical blank state, but rather from a completely replicated current state of the field. This eliminates errors caused by mismatches in the initial state, resulting in a smoother and more reliable alignment between the simulated future trajectory and the actual situation.

[0058] Specifically, the parallel injection includes at least two different candidate execution strategies: First strategy: An optimized operation strategy based on the resource prediction data, with the goal of maximizing the power generation of the entire station; Second strategy: A tracking operation strategy that receives and tracks preset power commands from external systems; The first strategy and the second strategy are executed synchronously under the same initial state in the advanced simulation.

[0059] The first strategy is an optimized operation strategy based on resource forecast data, aiming to maximize the power generation of the entire power station. This strategy represents the power station's pursuit of maximum benefit as an independent power generator. In the digital twin model, this strategy is instantiated as a real-time optimization controller. During the simulation, within each simulation step, this controller solves an optimization problem with the total grid-connected power generation within the simulation period, based on the resource forecast sequence accurate to the location of each power generation unit for a future preset time period, and considering the dynamic equipment constraints provided by the performance simulation layer.

[0060] For example, in a specific implementation process, during the simulation period Inside, discrete as Each step length. The station has... Each controllable power generation unit. For each simulation step... ( The first strategy solves the following optimization problem to determine the planned power of each unit. : The constraints include: in, It is based on the step size Resource forecast data Calculated unit Maximum theoretical power This represents the step size time interval.

[0061] The second strategy is a tracking operation strategy that receives and tracks preset power commands from an external system. This strategy represents the requirement for the power station, as a dispatchable unit of the power grid, to comply with the superior dispatch commands. In the simulation, this strategy is instantiated as a power tracking controller. It receives a future preset power command curve as input. At each step of the simulation, the controller's logic is to calculate the deviation between the current simulated total output power of the entire power station and the command value, and decompose this deviation into each controllable generating unit through an internal algorithm, with the goal of minimizing the power tracking error.

[0062] For example, in a specific implementation, given an external power command sequence At each step The second strategy solves a quadratic optimization problem, minimizing the tracking error and allocating power: Furthermore, the constraints are the same as those in the first strategy regarding equipment and security.

[0063] in, It can be a unit The preferred power point (e.g., MPPT point), coefficient Used to balance tracking accuracy and power generation efficiency.

[0064] In this embodiment, the essence of the comparative evaluation lies in the synchronous execution of the first and second strategies under the same initial state during advanced simulation. The simulation engine creates two or more identical, pre-initialized digital twin model copies. The controller logic of the first strategy is loaded into one copy, and the controller logic of the second strategy is loaded into the other. The two simulation processes are completely synchronized in time and executed in parallel computationally. Ultimately, two different future power curves, equipment operating condition curves, and corresponding sets of technical indicators are obtained. By simulating these two typical and often conflicting strategies in parallel, advanced parallel simulation allows for the prediction in advance: how much additional electricity might be gained in the future if the power generation maximization strategy is adhered to, but at the cost of power tracking error; conversely, how much potential power generation revenue would be lost if dispatch instructions are strictly followed. By optimizing the objective function and comprehensively evaluating the two sets of simulation results, the net benefits of different strategies can be clearly quantified and compared. This enables operators or intelligent decision-making systems to make the most beneficial choice based on the simulation and quantitative analysis of future scenarios.

[0065] Specifically, a simulation and deduction method for new energy power plants also includes: During the advanced simulation process, the simulation data under any candidate operation strategy is monitored in real time to see if it triggers the preset alarm conditions; if it is triggered, the simulation is immediately interrupted and an early warning report is generated, including the alarm strategy, alarm time and alarm content.

[0066] During the advanced simulation process, the system not only calculates the final result indicators but also performs real-time security scans across the entire simulation timeline. This is achieved through a dedicated security monitoring module that receives the simulation data streams of each candidate strategy in parallel.

[0067] Real-time monitoring of simulated operation data to determine if preset alarm conditions are triggered means that the monitoring module has a series of pre-set criteria and thresholds reflecting equipment safety and system stability. For example, this could be triggered if the simulated parameters of any power generation unit or critical component exceed safety thresholds, the simulated voltage of a key electrical node in the station exceeds normal operating range, or the simulated power of the collection line exceeds thermal stability limits. Monitoring is real-time; a judgment is made immediately after each time step of data is calculated in the simulation. Once the simulation path of a candidate strategy triggers any alarm condition, the simulation process for that strategy will be immediately paused or terminated without waiting for the entire preset simulation period to end.

[0068] By adding a crucial safety red line check function to the simulation, the simulation is not only used to find the optimal strategy but also to identify and eliminate bad strategies in advance. In actual operation, some strategies may lead to safety hazards such as equipment overheating and voltage exceeding limits. This embodiment can monitor these safety indicators in real time during the simulation. Once the simulated operation data touches the preset safety threshold, it immediately issues an alarm and stops the simulation of that strategy. This is equivalent to performing an automated safety audit before the strategy is implemented, effectively preventing the misuse of strategies that may increase benefits but could damage equipment or endanger system security.

[0069] This invention also provides a simulation and deduction system for new energy power plants, which applies the aforementioned method and includes: The data acquisition unit is used to acquire the operating status data of new energy power plants and the resource prediction data for a future preset period. A digital twin engine is used to synchronously construct a digital twin model of the site based on the operational status data. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operational strategy. The strategy management unit is used to load the resource prediction data as boundary conditions into the digital twin model of the site and inject at least two different candidate operation strategies in parallel. The simulation and deduction unit is used to drive the digital twin model of the site to perform advanced simulation and deduction, respectively simulating the operation process under the control of different candidate operation strategies within the future preset time period, and generating multiple sets of pre-simulation result data corresponding to each candidate strategy; The evaluation and decision-making unit is used to evaluate and compare the multiple sets of pre-simulation result data online based on a predefined optimization objective function, and output the optimal candidate running strategy as a strategy recommendation.

[0070] The functional explanations of each unit in this embodiment are the same as those in a new energy power station simulation and deduction method, and the technical effects are the same, so they will not be repeated here.

[0071] This invention also provides a computer-readable storage medium, which includes a stored program, wherein the program, when running, controls the device where the computer-readable storage medium is located to execute the steps of the aforementioned new energy power station simulation and deduction method.

[0072] The technical effects of this embodiment are the same as those of the simulation and deduction method for a new energy power station in the embodiment, and will not be repeated here.

[0073] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0074] This invention also provides a processor for running a program, wherein the program executes the aforementioned simulation and deduction method for a new energy power station.

[0075] The technical effects of this embodiment are the same as those of the simulation and deduction method for new energy power stations in Embodiment 1, and will not be repeated here.

[0076] In this embodiment, the processor may be a central processing unit (CPU), a controller, a microcontroller, or other data processing chip.

[0077] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0078] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0079] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0080] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the specification of the present invention.

Claims

1. A simulation and deduction method for new energy power stations, characterized in that, include: Acquire operational status data and resource forecast data for future preset time periods from new energy power plants; Based on the operational status data, a digital twin model of the site is constructed synchronously. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operational strategy. In the digital twin model of the site, the resource prediction data is loaded as a boundary condition, and at least two different candidate operation strategies are injected in parallel. The digital twin model of the station is driven to perform advanced simulation and deduction, respectively simulating the operation process under the control of different candidate operation strategies within the future preset time period, and generating multiple sets of pre-simulation result data corresponding to each candidate strategy; Based on a predefined optimization objective function, the multiple sets of pre-simulation result data are evaluated and compared online, and the optimal candidate running strategy is output as a strategy recommendation.

2. The simulation and deduction method for new energy power stations according to claim 1, characterized in that, The operational status data includes at least the real-time output power, switching status, available capacity, and temperature data of key components for each power generation unit.

3. The simulation and deduction method for new energy power stations according to claim 2, characterized in that, The synchronous construction of the digital twin model of the site based on the operational status data includes: The available capacity is set as the upper limit of the simulated power of the corresponding power generation unit in the performance simulation layer, and the temperature of the key component is used as the input parameter of the loss calculation module in the performance simulation layer.

4. The simulation and deduction method for a new energy power station according to claim 2, characterized in that, The synchronous construction of the digital twin model of the site includes: In a simulation server independent of the physical site control system, the simulated on / off status of each power generation unit is initialized based on the switch status in the operating status data; Based on the real-time output power and resource prediction data, the internal intermediate variables in the performance simulation layer are initialized so that the simulation start state of the digital twin model of the power station matches the current actual operating state of the physical power station.

5. The simulation and deduction method for a new energy power station according to claim 2, characterized in that, The parallel injection includes at least two different candidate execution strategies: First strategy: An optimized operation strategy based on the resource prediction data, with the goal of maximizing the power generation of the entire station; Second strategy: A tracking operation strategy that receives and tracks preset power commands from external systems; The first strategy and the second strategy are executed synchronously under the same initial state in the advanced simulation.

6. The simulation and deduction method for a new energy power station according to claim 1, characterized in that, Also includes: During the advanced simulation process, the simulation data under any candidate operating strategy is monitored in real time to see if it triggers a preset alarm condition. If triggered, the simulation will be immediately interrupted, and an early warning report will be generated, including the trigger strategy, trigger time, and trigger content.

7. The simulation and deduction method for a new energy power station according to claim 1, characterized in that, The objective function is calculated as follows: Based on preset multi-dimensional weighting coefficients, multiple key performance indicators in the multiple sets of pre-simulation result data are weighted and calculated to generate a comprehensive score corresponding to each candidate running strategy.

8. A simulation and deduction system for new energy power stations, characterized in that, The method for simulating and extrapolating a new energy power station according to any one of claims 1 to 7 includes: The data acquisition unit is used to acquire the operating status data of new energy power plants and the resource prediction data for a future preset period. A digital twin engine is used to synchronously construct a digital twin model of the site based on the operational status data. The digital twin model includes a performance simulation layer parameterized according to real-time equipment status and a strategy simulation layer instantiated according to the current operational strategy. The strategy management unit is used to load the resource prediction data as boundary conditions into the digital twin model of the site and inject at least two different candidate operation strategies in parallel. The simulation and deduction unit is used to drive the digital twin model of the site to perform advanced simulation and deduction, respectively simulating the operation process under the control of different candidate operation strategies within the future preset time period, and generating multiple sets of pre-simulation result data corresponding to each candidate strategy; The evaluation and decision-making unit is used to evaluate and compare the multiple sets of pre-simulation result data online based on a predefined optimization objective function, and output the optimal candidate running strategy as a strategy recommendation.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the steps of the simulation and deduction method for a new energy power station as described in any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes a simulation and deduction method for a new energy power station as described in any one of claims 1 to 7.

Images