Flexible control system, method, equipment and medium for power plant

Abstract

The invention discloses a flexible control system, method and device for a power plant and a medium, and the system comprises a load prediction module which is used for predicting the load demand data of the power plant at any time in the future according to the historical state data and real-time state data of a power grid; the control strategy optimization module is used for calculating the load demand data by using an MPC model prediction control technology and an ADMM alternating direction multiplier method to obtain a flexible operation strategy; and the strategy execution module is used for adjusting the real-time operation state of the power plant according to the flexible operation strategy. According to the invention, the control strategy optimization module is utilized to calculate and obtain a flexible operation strategy, so that the flexibility and response capability effects of the power plant are improved under the conditions of rapid load change and complex operation conditions; the strategy execution module is used for adjusting the real-time operation state of the power plant according to the flexible operation strategy, and the stability, reliability and economic benefits of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization control, and in particular to a flexible control system, method, equipment and medium of a power plant. Background Art

[0002] As the world's requirements for low-carbon emissions become increasingly stringent, the power industry faces tremendous pressure. We have accumulated rich experience in the long-term stable operation of traditional combustion and gas-fired thermal power plants, but with the large-scale access of renewable energy (such as wind power and solar energy), the operation of the power grid faces new challenges. Due to the volatility and intermittency of renewable energy, the load changes in the power system are more frequent and unpredictable, which puts higher requirements on the operational flexibility of power plants.

[0003] Traditional power plants mostly use a regulation method based on proportional-integral-differential (PID) control, which has good system stability and simplicity. However, facing the rapid load changes and complex operating conditions after the access of renewable energy, its response speed and regulation accuracy are obviously insufficient. PID control cannot foresee future disturbances in the system and it is difficult to achieve optimal control in a complex and dynamic power system.

[0004] Therefore, how to better integrate renewable energy and energy storage devices in complex low-carbon energy consumption systems to achieve stable, efficient and flexible operation is an urgent problem to be solved. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the defects of the existing optimization control methods in the prior art, such as weak flexibility, slow response capability and poor effect under the conditions of rapid load changes and complex operating conditions of power plants, and to provide a flexible control system, method, equipment and medium for power plants.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] In a first aspect, the present invention provides a flexible control system for a power plant, the flexible control system comprising:

[0008] The load forecasting module is used to predict the load demand data of the power plant at any time in the future based on the historical status data and real-time status data of the power grid;

[0009] A control strategy optimization module, used to calculate the load demand data using MPC model predictive control technology and ADMM alternating direction multiplier method to obtain a flexible operation strategy;

[0010] The strategy execution module is used to adjust the real-time operation state of the power plant according to the flexible operation strategy.

[0011] Preferably, the control strategy optimization module includes a physical modeling unit and a first strategy calculation unit;

[0012] The physical modeling unit is used to construct an operating system model, and predict the operating system state data of the power plant at a future time through the operating system model according to the real-time state data; the operating system model includes at least one of a turbine model, a boiler model and a generator model;

[0013] The first strategy calculation unit is used to calculate the first operation strategy at the current moment based on the operation system state data using the MPC model predictive control technology.

[0014] Preferably, the control strategy optimization module further includes an energy storage modeling unit and a second strategy calculation unit;

[0015] The energy storage modeling unit is used to construct an energy storage system model, and predict the energy storage system state data of the power plant at a future time through the energy storage system model according to the real-time state data; the energy storage system model includes a battery model and a flywheel model;

[0016] The second strategy calculation unit is used to calculate the second operation strategy at the current moment based on the energy storage system state data using the MPC model predictive control technology.

[0017] Preferably, the control strategy optimization module further includes a strategy optimization unit;

[0018] The strategy optimization unit is used to associate the energy storage system model with the operation system model using the MPC model predictive control technology, and to optimize the first operation strategy and the second operation strategy using the ADMM alternating direction multiplier method to obtain the flexible operation strategy.

[0019] In a second aspect, the present invention provides a flexible control method for a power plant, the flexible control method comprising:

[0020] The load demand data of the power plant at any time in the future is predicted based on the historical status data and real-time status data of the power grid;

[0021] The load demand data is calculated using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy;

[0022] The real-time operation state of the power plant is adjusted according to the flexible operation strategy.

[0023] Preferably, the step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain the flexible operation strategy includes:

[0024] Constructing an operation system model, and predicting the operation system state data of the power plant at a future time through the operation system model according to the real-time state data; the operation system model includes at least one of a turbine model, a boiler model and a generator model;

[0025] The MPC model predictive control technology is used to calculate the operating system state data to obtain the first operating strategy at the current moment.

[0026] Preferably, the step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain the flexible operation strategy also includes:

[0027] Constructing an energy storage system model, and predicting the energy storage system status data of the power plant at a future time through the energy storage system model according to the real-time status data; the energy storage system model includes a battery model and a flywheel model;

[0028] The MPC model predictive control technology is used to calculate the energy storage system state data to obtain a second operation strategy at the current moment.

[0029] Preferably, the step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain the flexible operation strategy also includes:

[0030] The MPC model predictive control technology is used to associate the energy storage system model with the operating system model, and the ADMM alternating direction multiplier method is used to optimize the first operating strategy and the second operating strategy to obtain the flexible operating strategy.

[0031] In a third aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the flexible control method of a power plant as described above when executing the computer program.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the flexible control method of a power plant as described above is implemented.

[0033] The positive and progressive effects of the present invention are: the load prediction module predicts the load demand data of the power plant at any time in the future based on the historical state data and real-time state data of the power grid; the control strategy optimization module calculates the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy; the strategy execution module adjusts the real-time operation state of the power plant according to the flexible operation strategy. The present invention uses the control strategy optimization module to calculate the flexible operation strategy, so that the flexibility and responsiveness of the power plant are improved under rapid load changes and complex operating conditions; the strategy execution module is used to adjust the real-time operation state of the power plant according to the flexible operation strategy to enhance the stability, reliability and economic benefits of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of the first module of the flexible control system of a power plant according to Example 1 of the present invention.

[0035] Figure 2 This is a schematic diagram of the second module of the flexible control system of a power plant according to Example 1 of the present invention.

[0036] Figure 3 This is a first flow chart of the flexible control method for a power plant according to Embodiment 2 of the present invention.

[0037] Figure 4 This is a second flow chart of the flexible control method for a power plant according to Embodiment 2 of the present invention.

[0038] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing a flexible control method for a power plant according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0040] Example 1

[0041] The flexible control system of the power plant in this embodiment is as follows: Figure 1 As shown, the flexible control system includes:

[0042] The load prediction module 110 is used to predict the load demand data of the power plant at any time in the future based on the historical state data and real-time state data of the power grid;

[0043] A control strategy optimization module 120 is used to calculate the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy;

[0044] The strategy execution module 130 is used to adjust the real-time operation status of the power plant according to the flexible operation strategy.

[0045] The load forecasting module 110 uses a deep learning algorithm to calculate the historical status data and real-time status data of the power grid to predict the load demand data of the power plant at any time in the future. The deep learning algorithm improves the accuracy of predicting the load demand data of the power plant at any time in the future.

[0046] The control strategy optimization module 120 is based on the model predictive control (MPC) technology, combined with the alternating direction multiplier method (ADMM) to solve the distributed optimization problem, so as to obtain a flexible operation strategy including adjusting the output power of the power plant. Traditional power plants are often difficult to adjust quickly and flexibly when the load fluctuates greatly. After adopting the MPC technology, the power plant can dynamically adjust the power generation through real-time prediction of future load demand. The dual mechanism of prediction and optimization enables the power plant to respond quickly when facing complex load fluctuations, avoiding the deterioration of power quality or instability of the power grid due to delayed response. Especially in the context of the access of renewable energy (such as wind power and solar energy), the application of MPC has greatly improved the load regulation capability of the power plant.

[0047] The strategy execution module 130 executes the flexible operation strategy to adjust the operation status of the power plant in real time, and displays the operation status of the power plant after the execution strategy is adjusted, such as the fuel supply rate and the grid balance. The flexible operation strategy can dynamically adjust the fuel consumption according to the predicted load demand, thereby improving the fuel utilization rate and reducing unnecessary fuel waste. In practical applications, the fuel optimization strategy can not only reduce the operating cost of the power plant, but also effectively reduce greenhouse gas emissions and promote the realization of environmental protection goals.

[0048] In an alternative embodiment, Figure 2 As shown, the control strategy optimization module 120 includes a physical modeling unit 121 and a first strategy calculation unit 122;

[0049] The physical modeling unit 121 is used to construct an operating system model and predict the operating system state data of the power plant at a future time through the operating system model according to the real-time state data; the operating system model includes at least one of a turbine model, a boiler model and a generator model;

[0050] The first strategy calculation unit 122 is used to calculate the first operation strategy at the current moment based on the operation system state data by using the MPC model predictive control technology.

[0051] Modeling of the flexible operation system of the power plant is one of the cores of the MPC solution. Each power plant includes multiple dynamically coupled subsystems, such as a steam turbine subsystem, a boiler subsystem, and a generator subsystem. In order to ensure control accuracy, the dynamic behavior of the power plant must be modeled through nonlinear differential equations. The physical modeling unit 121 constructs a steam turbine model, a boiler model, and a generator model, and predicts the operating system status data through any model based on the real-time status data.

[0052] The steam turbine is one of the core equipment of the power plant. Its dynamic response directly affects the regulation ability of power generation. The dynamic equation of the steam turbine model is expressed by the following nonlinear model:

[0053]

[0054] in, represents the output power of the steam turbine, u t Indicates the control input, usually the valve opening, v t represents system disturbances, such as load changes or fluctuations in wind power generation, and the control goal of the steam turbine is to maintain a stable output power when the load fluctuates.

[0055] The dynamic behavior of the boiler is complex, including fuel supply, combustion process and heat transfer process. The dynamic equation of the boiler model is expressed as:

[0056]

[0057] in, represents the temperature of the boiler, u b represents the fuel supply rate, P b Indicates steam pressure. MPC achieves dynamic control of boiler temperature and pressure by adjusting the fuel supply rate, thereby ensuring stable operation of the turbine.

[0058] The modeling of the generator is relatively simple. Its output voltage and frequency are mainly affected by the rotor speed and electromagnetic field strength. The control equation of the generator model is simplified to a linear model:

[0059] V g =K g ω r

[0060] Among them, V g Indicates the output voltage of the generator, K g represents the proportionality constant, ω r Indicates the rotor speed. By adjusting the output power of the steam turbine, the output of the generator is indirectly controlled.

[0061] In an optional embodiment, the control strategy optimization module 120 further includes an energy storage modeling unit 123 and a second strategy calculation unit 124;

[0062] The energy storage modeling unit 123 is used to construct an energy storage system model and predict the energy storage system state data of the power plant at a future time through the energy storage system model according to the real-time state data; the energy storage system model includes a battery model and a flywheel model;

[0063] The second strategy calculation unit 124 is used to calculate the second operation strategy at the current moment based on the energy storage system state data using the MPC model predictive control technology.

[0064] In flexible control, energy storage systems (such as batteries, flywheels, etc.) can be used as an important means of regulation to help power plants cope with fluctuations in renewable energy. Energy storage systems can store excess electricity when electricity demand is too low, and release energy during peak load periods or when renewable energy generation is insufficient, thereby reducing the load regulation pressure of power plants, extending the service life of equipment, and improving the overall energy efficiency of the system.

[0065] The energy storage system model constructed by the energy storage modeling unit 123 can be expressed as:

[0066]

[0067] Where E(t) represents the current energy storage level of the energy storage device, E(t+1) represents the energy storage level of the energy storage device at the next moment, and P in (t) represents the charging power, P out (t) represents the discharge power, η charge and η discharge Represent the charging and discharging efficiencies respectively.

[0068] The scheduling optimization goal of the energy storage system is to decide when to charge or discharge based on the system's load conditions and electricity price signals. MPC determines the best operating strategy for the energy storage system by predicting future load changes in real time, thereby achieving the goal of optimal system operation.

[0069] In an optional embodiment, the control strategy optimization module 120 further includes a strategy optimization unit 125;

[0070] The strategy optimization unit 125 is used to associate the energy storage system model with the operation system model using the MPC model predictive control technology, and to optimize the first operation strategy and the second operation strategy to obtain a flexible operation strategy using the ADMM alternating direction multiplier method.

[0071] The MPC in the strategy optimization unit 125 integrates the energy storage system into the power plant control, so that the power plant can optimize the energy storage scheduling at multiple moments in the future while meeting the current power demand. The optimization problem is expressed as:

[0072]

[0073] Among them, C power (i) represents the power generation cost of the power plant, C storage (i) represents the operating cost of the energy storage system. MPC reduces the total operating cost of the system by optimizing the charging and discharging behavior of the energy storage system.

[0074] Since the traditional centralized optimization method has a computing bottleneck in large-scale power plant applications, the present invention improves the real-time solving capability through a distributed optimization strategy. The alternating direction method of multipliers (ADMM) is a commonly used distributed optimization algorithm, which can decompose the overall optimization problem into multiple sub-problems, each of which is solved independently and coordinated in the iterative process.

[0075] The basic principle of ADMM is to coordinate the optimization behaviors of different subsystems by introducing Lagrange multipliers. The formula is as follows:

[0076] L(x,u,λ)=∑ i [f i (x i ,u i )+λ i (x i -z)]

[0077] Among them, f i (x i ,u i ) represents the objective function of the steam turbine model, boiler model, generator model or energy storage system model, z represents the global variable, λ i represents the Lagrange multiplier.

[0078] ADMM optimizes the variables of each subsystem separately and adjusts the mutual influence between subsystems through Lagrange multipliers to finally achieve the global optimal solution.

[0079]

[0080] V(s) represents the true function corresponding to each model, which indicates the expected value of future cumulative returns starting from the current state s.

[0081] V(s)=max a [R(s,a)+γE s′ V(s′)]

[0082] R(s,a) represents the immediate profit function, γ represents the discount factor, 0<γ≤1, E s′ V(s′) represents the expected value of the next state s′.

[0083] The approximate value function represents the approximate value of V(s) and depends on the parameter vector θ. Through approximation, the complex recursive calculation of directly solving V(s) is avoided. Represents a basis function or a characteristic function, which means converting the state s into a component of the feature space, used to represent the association between states. Typical choices include: polynomial function, radial basis function, neural network activation function. i Represents the weight parameter, which is used to adjust the contribution of the basis function. This parameter is obtained through training. N represents the number of basis functions, which affects the representation ability and computational complexity of the value function.

[0084] In this embodiment, a flexible control system of a power plant is provided, wherein the load prediction module predicts the load demand data of the power plant at any time in the future based on the historical state data and real-time state data of the power grid; the control strategy optimization module calculates the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy; the strategy execution module adjusts the real-time operation state of the power plant according to the flexible operation strategy. The present invention uses the control strategy optimization module to calculate the flexible operation strategy, so that the flexibility and responsiveness of the power plant are improved under rapid load changes and complex operating conditions; the strategy execution module is used to adjust the real-time operation state of the power plant according to the flexible operation strategy to enhance the stability, reliability and economic benefits of the system.

[0085] Example 2

[0086] The flexible control method of the power plant in this embodiment is as follows: Figure 3 As shown, the flexible control method includes:

[0087] S21, predicting the load demand data of the power plant at any time in the future based on the historical status data and real-time status data of the power grid;

[0088] S22, using MPC model predictive control technology and ADMM alternating direction multiplier method to calculate the load demand data to obtain a flexible operation strategy;

[0089] S23. Adjust the real-time operating status of the power plant according to the flexible operation strategy.

[0090] For the above step S21, a deep learning algorithm is used to calculate the historical status data and real-time status data of the power grid to predict the load demand data of the power plant at any time in the future. The accuracy of predicting the load demand data of the power plant at any time in the future is improved by the deep learning algorithm.

[0091] For the above step S22, based on the model predictive control (MPC) technology, the alternating direction multiplier method (ADMM) is combined to solve the distributed optimization problem to obtain a flexible operation strategy including adjusting the output power of the power plant. Traditional power plants are often difficult to adjust quickly and flexibly when the load fluctuates greatly. After adopting the MPC technology, the power plant can dynamically adjust the power generation through real-time prediction of future load demand. The dual mechanism of prediction and optimization enables the power plant to respond quickly when faced with complex load fluctuations, avoiding the deterioration of power quality or instability of the power grid due to delayed response. Especially in the context of the access of renewable energy (such as wind power and solar energy), the application of MPC has greatly improved the load regulation capability of the power plant.

[0092] For the above step S23, a flexible operation strategy is executed to adjust the operating status of the power plant in real time, and the operation status of the power plant after the execution strategy adjustment is displayed, such as the fuel supply rate and the grid balance. The flexible operation strategy can dynamically adjust the fuel consumption according to the predicted load demand, thereby improving the fuel utilization rate and reducing unnecessary fuel waste. In practical applications, the fuel optimization strategy can not only reduce the operating cost of the power plant, but also effectively reduce greenhouse gas emissions and promote the realization of environmental protection goals.

[0093] In an alternative embodiment, Figure 4 As shown, step S22 includes:

[0094] S221, constructing an operation system model, and predicting the operation system state data of the power plant at a future time through the operation system model according to the real-time state data; the operation system model includes at least one of a steam turbine model, a boiler model and a generator model;

[0095] S222: Utilize the MPC model predictive control technology to calculate the operating system state data to obtain the first operating strategy at the current moment.

[0096] Modeling of the flexible operation system of a power plant is one of the cores of the MPC solution. Each power plant includes multiple dynamically coupled subsystems, such as turbine subsystem, boiler subsystem and generator subsystem. In order to ensure control accuracy, the dynamic behavior of the power plant must be modeled through nonlinear differential equations, and turbine models, boiler models and generator models must be constructed. The operating system status data can be predicted through any model based on the real-time status data.

[0097] The steam turbine is one of the core equipment of the power plant. Its dynamic response directly affects the regulation ability of power generation. The dynamic equation of the steam turbine model is expressed by the following nonlinear model:

[0098]

[0099] in, represents the output power of the steam turbine, u t Indicates the control input, usually the valve opening, v t represents system disturbances, such as load changes or fluctuations in wind power generation, and the control goal of the steam turbine is to maintain a stable output power when the load fluctuates.

[0100] The dynamic behavior of the boiler is complex, including fuel supply, combustion process and heat transfer process. The dynamic equation of the boiler model is expressed as:

[0101]

[0102] in, represents the temperature of the boiler, u b represents the fuel supply rate, P b Indicates steam pressure. MPC achieves dynamic control of boiler temperature and pressure by adjusting the fuel supply rate, thereby ensuring stable operation of the turbine.

[0103] The modeling of the generator is relatively simple. Its output voltage and frequency are mainly affected by the rotor speed and electromagnetic field strength. The control equation of the generator model is simplified to a linear model:

[0104] V g =K g ω r

[0105] Among them, V g Indicates the output voltage of the generator, K g represents the proportionality constant, ω r Indicates the rotor speed. By adjusting the output power of the steam turbine, the output of the generator is indirectly controlled.

[0106] In an optional implementation, step S22 further includes:

[0107] S223, constructing an energy storage system model, and predicting energy storage system status data of the power plant at a future time through the energy storage system model according to the real-time status data; the energy storage system model includes a battery model and a flywheel model;

[0108] S224. Utilize the MPC model predictive control technology to calculate the energy storage system state data to obtain the second operation strategy at the current moment.

[0109] In flexible control, energy storage systems (such as batteries, flywheels, etc.) can be used as an important means of regulation to help power plants cope with fluctuations in renewable energy. Energy storage systems can store excess electricity when electricity demand is too low, and release energy during peak load periods or when renewable energy generation is insufficient, thereby reducing the load regulation pressure of power plants, extending the service life of equipment, and improving the overall energy efficiency of the system.

[0110] The constructed energy storage system model can be expressed as:

[0111]

[0112] Where E(t) represents the current energy storage level of the energy storage device, E(t+1) represents the energy storage level of the energy storage device at the next moment, and P in (t) represents the charging power, P out (t) represents the discharge power, η charge and η discharge Represent the charging and discharging efficiencies respectively.

[0113] The scheduling optimization goal of the energy storage system is to decide when to charge or discharge based on the system's load conditions and electricity price signals. MPC determines the best operating strategy for the energy storage system by predicting future load changes in real time, thereby achieving the goal of optimal system operation.

[0114] In an optional implementation, step S22 further includes:

[0115] S225, using MPC model predictive control technology to associate the energy storage system model with the operation system model, and using ADMM alternating direction multiplier method to optimize the first operation strategy and the second operation strategy to obtain a flexible operation strategy.

[0116] By integrating the energy storage system into the power plant control, MPC enables the power plant to meet the current power demand while optimizing the energy storage scheduling at multiple times in the future. The optimization problem is expressed as:

[0117]

[0118] Among them, C power (i) represents the power generation cost of the power plant, C storage (i) represents the operating cost of the energy storage system. MPC reduces the total operating cost of the system by optimizing the charging and discharging behavior of the energy storage system.

[0119] Since the traditional centralized optimization method has a computing bottleneck in large-scale power plant applications, the present invention improves the real-time solving capability through a distributed optimization strategy. The alternating direction method of multipliers (ADMM) is a commonly used distributed optimization algorithm, which can decompose the overall optimization problem into multiple sub-problems, each of which is solved independently and coordinated in the iterative process.

[0120] The basic principle of ADMM is to coordinate the optimization behaviors of different subsystems by introducing Lagrange multipliers. The formula is as follows:

[0121] L(x,u,λ)=∑ i [f i (x i ,u i )+λ i (x i -z)]

[0122] Among them, f i (x i ,u i ) represents the objective function of the steam turbine model, boiler model, generator model or energy storage system model, z represents the global variable, λ i represents the Lagrange multiplier.

[0123] ADMM optimizes the variables of each subsystem separately and adjusts the mutual influence between subsystems through Lagrange multipliers to finally achieve the global optimal solution.

[0124]

[0125] V(s) represents the true function corresponding to each model, which indicates the expected value of future cumulative returns starting from the current state s.

[0126] V(s)=max a [R(s,a)+γE s′ V(s′)]

[0127] R(s,a) represents the immediate profit function, γ represents the discount factor, 0<γ≤1, E s′ V(s′) represents the expected value of the next state s′.

[0128] The approximate value function represents the approximate value of V(s) and depends on the parameter vector θ. Through approximation, the complex recursive calculation of directly solving V(s) is avoided. Represents a basis function or a characteristic function, which means converting the state s into a component of the feature space, used to represent the association between states. Typical choices include: polynomial function, radial basis function, neural network activation function.i Represents the weight parameter, which is used to adjust the contribution of the basis function. This parameter is obtained through training. N represents the number of basis functions, which affects the representation ability and computational complexity of the value function.

[0129] In this embodiment, a flexible control system of a power plant is provided, which predicts the load demand data of the power plant at any time in the future based on the historical state data and real-time state data of the power grid; uses the MPC model predictive control technology and the ADMM alternating direction multiplier method to calculate the load demand data to obtain a flexible operation strategy; and adjusts the real-time operation state of the power plant according to the flexible operation strategy. The present invention uses a control strategy optimization module to calculate a flexible operation strategy, so that the flexibility and responsiveness of the power plant are improved under rapid load changes and complex operating conditions; uses a strategy execution module to adjust the real-time operation state of the power plant according to the flexible operation strategy, thereby enhancing the stability, reliability and economic benefits of the system.

[0130] Example 3

[0131] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the flexible control method of the power plant in embodiment 2 is implemented when the processor executes the program. Figure 5 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0132] like Figure 5 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0133] The bus 93 includes a data bus, an address bus, and a control bus.

[0134] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0135] The memory 92 may also include a program / utility 925 having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0136] The processor 91 executes various functional applications and data processing by running the computer programs stored in the memory 92, such as the flexible control method of the power plant in the second embodiment of the present invention.

[0137] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the model generating device 90 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 96. Figure 5 As shown, the network adapter 96 communicates with other modules of the model-generated device 90 via the bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0138] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0139] Example 4

[0140] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the flexible control method of a power plant in Embodiment 2 are implemented.

[0141] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0142] In a possible implementation manner, the present invention may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps in the flexible control method for a power plant in Example 2.

[0143] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0144] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A flexible control system for a power plant, characterized in that: The flexible control system comprises: The load forecasting module is used to predict the load demand data of the power plant at any time in the future based on the historical status data and real-time status data of the power grid; A control strategy optimization module, used to calculate the load demand data using MPC model predictive control technology and ADMM alternating direction multiplier method to obtain a flexible operation strategy; The strategy execution module is used to adjust the real-time operation state of the power plant according to the flexible operation strategy.

2. The flexible control system of a power plant according to claim 1, characterized in that: The control strategy optimization module includes a physical modeling unit and a first strategy calculation unit; The physical modeling unit is used to construct an operating system model, and predict the operating system state data of the power plant at a future time through the operating system model according to the real-time state data; the operating system model includes at least one of a turbine model, a boiler model and a generator model; The first strategy calculation unit is used to calculate the first operation strategy at the current moment based on the operation system state data using the MPC model predictive control technology.

3. The flexible control system of a power plant according to claim 2, characterized in that: The control strategy optimization module also includes an energy storage modeling unit and a second strategy calculation unit; The energy storage modeling unit is used to construct an energy storage system model, and predict the energy storage system state data of the power plant at a future time through the energy storage system model according to the real-time state data; the energy storage system model includes a battery model and a flywheel model; The second strategy calculation unit is used to calculate the second operation strategy at the current moment based on the energy storage system state data using the MPC model predictive control technology.

4. The flexible control system of a power plant according to claim 3, characterized in that: The control strategy optimization module also includes a strategy optimization unit; The strategy optimization unit is used to associate the energy storage system model with the operation system model using the MPC model predictive control technology, and to optimize the first operation strategy and the second operation strategy using the ADMM alternating direction multiplier method to obtain the flexible operation strategy.

5. A flexible control method for a power plant, characterized in that: The flexible control method comprises: The load demand data of the power plant at any time in the future is predicted based on the historical status data and real-time status data of the power grid; The load demand data is calculated using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy; The real-time operation state of the power plant is adjusted according to the flexible operation strategy.

6. The flexible control method of a power plant according to claim 5, characterized in that: The step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy includes: Constructing an operation system model, and predicting the operation system state data of the power plant at a future time through the operation system model according to the real-time state data; the operation system model includes at least one of a turbine model, a boiler model and a generator model; The MPC model predictive control technology is used to calculate the operating system state data to obtain the first operating strategy at the current moment.

7. The flexible control method of a power plant according to claim 6, characterized in that: The step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy also includes: Constructing an energy storage system model, and predicting the energy storage system status data of the power plant at a future time through the energy storage system model according to the real-time status data; the energy storage system model includes a battery model and a flywheel model; The MPC model predictive control technology is used to calculate the energy storage system state data to obtain a second operation strategy at the current moment.

8. The flexible control method of a power plant according to claim 7, characterized in that: The step of calculating the load demand data using the MPC model predictive control technology and the ADMM alternating direction multiplier method to obtain a flexible operation strategy also includes: The MPC model predictive control technology is used to associate the energy storage system model with the operating system model, and the ADMM alternating direction multiplier method is used to optimize the first operating strategy and the second operating strategy to obtain the flexible operating strategy.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the flexible control method of the power plant as claimed in any one of claims 5 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the flexible control method for a power plant according to any one of claims 5 to 8 is implemented.

Images