A deep peak regulation optimization control method for thermal power generating units under large-scale grid-connected conditions

Abstract

The application discloses a kind of large-scale grid-connected conditions under thermal power generating unit depth peak shaving optimization control method, comprising: build large-scale grid-connected power system model, and based on power system model, construct upper layer new energy carrying capacity evaluation function and lower layer power grid stability evaluation function;Using differential evolution algorithm, with upper layer new energy carrying capacity evaluation function and lower layer power grid stability evaluation function jointly constitute fitness function, the output scheme of each power generation unit containing thermal power generating unit is optimized and solved, and the optimal output of thermal power generating unit at depth peak shaving is obtained;Real-time monitoring of the current power generation of thermal power generating unit, and calculate the deviation of current power generation and optimal output;Deviation is input to neural network PID controller, and the operating control quantity required for thermal power generating unit to achieve optimal output is calculated;Operating control quantity is sent to the actuator of thermal power generating unit, to adjust the actual output of thermal power generating unit, complete depth peak shaving optimization control.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically, to a deep peak-shaving optimization control method for thermal power units under large-scale grid connection conditions. Background Technology

[0002] Against the backdrop of global energy scarcity, alleviating energy shortages has become a common goal for all countries, and research related to energy transition has become a widespread trend. In this process, new energy sources such as wind, solar, and hydropower are seeing their proportion in the current power structure steadily increase due to their significant advantages of being clean and sustainable. However, with the large-scale integration of new energy sources into the power grid, the stable operation of the power system also faces new challenges and difficulties. Because the power generation capacity of new energy sources is highly dependent on natural conditions, their output exhibits strong randomness with changes in the natural environment. This randomness can easily lead to power imbalances in the grid after integration, resulting in problems such as frequency fluctuations and voltage instability. As a representative of traditional power generation models, thermal power generation remains the mainstay of power supply. Unlike new energy generation, thermal power is driven by coal combustion and possesses strong controllability and operational stability. In scenarios of large-scale grid integration of new energy sources, thermal power units, as the ballast stone for the stable operation of the power system, need to undertake deep peak-shaving tasks to ensure a continuous and stable power supply by balancing the fluctuations in new energy generation. Against this backdrop, the frequency of thermal power units participating in deep peak-shaving is constantly increasing, placing higher demands on their peak-shaving control response capabilities.

[0003] The quantitative evaluation indicators for system frequency stability under deep peak shaving are lacking, and there is a lack of optimization for load allocation under deep peak shaving. Therefore, it is necessary to consider the impact of deep peak shaving of thermal power units on frequency regulation capability and system frequency stability, propose active power regulation capability evaluation indicators, construct evaluation models, and on this basis, consider a system load allocation optimization model for the primary frequency regulation capability of deep peak shaving units to improve system frequency stability under deep peak shaving. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method for deep peak shaving optimization control of thermal power units under large-scale grid connection conditions.

[0005] According to one aspect of the present invention, a method for deep peak shaving optimization control of thermal power units under large-scale grid connection conditions is provided, comprising: A large-scale grid-connected power system model including thermal power units, wind power generation units, and photovoltaic power generation units was constructed. Based on the power system model, an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function were constructed. The differential evolution algorithm is used to optimize the output scheme of each power generation unit including thermal power units by using the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function to form a fitness function, and to obtain the optimal output of thermal power units during deep peak shaving. Real-time monitoring of the current power generation of thermal power units, and calculation of the deviation between the current power generation and the optimal output; The deviation is input to the neural network PID controller, which tunes the proportional, integral, and derivative coefficients online based on the input state variables and calculates the operating control quantities required for the thermal power unit to achieve optimal output. The operating control quantities are sent to the actuators of the thermal power units to adjust the actual output of the thermal power units and complete the deep peak shaving optimization control.

[0006] Optionally, the processing model expression for each power supply unit in the power system model is as follows: In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , Representative moment t The operating temperature and reference temperature of the photovoltaic panel.

[0007] Optionally, the expression for the upper-level new energy carrying capacity assessment function is: In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. The expression for the lower-level power grid stability assessment function is: in, In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

[0008] Optionally, the fitness function can be expressed as: In the formula, Representing the One solution The fitness function; , Representing the One solution The corresponding upper and lower level evaluation function values; , This represents the evaluation function of the upper and lower layers.

[0009] Optionally, the expression for the operation control variable is: In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and power generation capacity. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , The coefficients representing the proportional, integral, and derivative of the optimized neural network; Represents real-time power generation and optimal output. The deviation between them.

[0010] Optionally, the neural network PID controller is tuned online based on the input state variables, including: Input the state variables of the thermal power unit into the neural network PID controller State variables include output deviation, deviation change rate, and historical control variables; Based on state variables, through a nonlinear activation function Calculate the hidden layer output : In the formula, , This represents the weights and biases of the hidden layer network.

[0011] Based on the hidden layer output Calculate the output of the output layer, that is , , .

[0012] In the formula, , , These represent the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

[0013] According to another aspect of the present invention, a deep peak-shaving optimization control device for thermal power units under large-scale grid connection conditions is provided, comprising: The module is used to build a large-scale grid-connected power system model that includes thermal power units, wind power generation units and photovoltaic power generation units, and based on the power system model, to build an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function. The solution module is used to optimize the output scheme of each power generation unit including thermal power units by employing the differential evolution algorithm, which uses the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function to form a fitness function, thereby obtaining the optimal output of thermal power units during deep peak shaving. The first calculation module is used to monitor the current power generation of the thermal power unit in real time and calculate the deviation between the current power generation and the optimal output. The second calculation module is used to input the deviation to the neural network PID controller. The neural network PID controller tunes the proportional, integral, and derivative coefficients online according to the input state variables and calculates the operating control quantities required for the thermal power unit to achieve optimal output. The control module is used to send operating control quantities to the actuators of the thermal power unit to adjust the actual output of the thermal power unit and complete deep peak shaving optimization control.

[0014] Optionally, the processing model expression for each power supply unit in the power system model is as follows: In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , Representative moment t The operating temperature and reference temperature of the photovoltaic panel.

[0015] Optionally, the expression for the upper-level new energy carrying capacity assessment function is: In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. The expression for the lower-level power grid stability assessment function is: in, In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

[0016] Optionally, the fitness function can be expressed as: In the formula, Representing the One solution The fitness function; , Representing the One solution The corresponding upper and lower level evaluation function values; , This represents the evaluation function of the upper and lower layers.

[0017] Optionally, the expression for the operation control variable is: In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and power generation capacity. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , The coefficients representing the proportional, integral, and derivative of the optimized neural network; Represents real-time power generation and optimal output. The deviation between them.

[0018] Optionally, the neural network PID controller is tuned online based on the input state variables, including: Input the state variables of the thermal power unit into the neural network PID controller State variables include output deviation, deviation change rate, and historical control variables; Based on state variables, through a nonlinear activation function Calculate the hidden layer output : In the formula, , This represents the weights and biases of the hidden layer network.

[0019] Based on the hidden layer output Calculate the output of the output layer, that is , , .

[0020] In the formula, , , These represent the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0022] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0023] Therefore, this invention proposes a deep peak-shaving optimization control method for thermal power units under large-scale grid-connected conditions. It integrates a two-layer evaluation function into the algorithm's fitness function and solves the optimal output plan through swarm intelligence search, effectively overcoming the limitation of "local optima" in traditional peak-shaving strategies. This ensures that the output of thermal power units can match the fluctuations in renewable energy while also considering their own operational economy and safety. By calculating the deviation between the actual output and the optimal output of the thermal power unit in real time, the nonlinear fitting capability of neural networks is used to dynamically optimize the PID parameters, achieving rapid adjustment of the control quantity. Attached Figure Description

[0024] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures: Figure 1 This is a flowchart illustrating a deep peak-shaving optimization control method for thermal power units under large-scale grid-connected conditions, provided by an exemplary embodiment of the present invention. Figure 2 This is another flowchart illustrating the deep peak-shaving optimization control method for thermal power units under large-scale grid-connected conditions provided by an exemplary embodiment of the present invention; Figure 3 This is a schematic diagram of a power system structure model under large-scale grid connection of new energy sources provided by an exemplary embodiment of the present invention; Figure 4 This is a schematic diagram of a control model based on neural network PID provided in an exemplary embodiment of the present invention; Figure 5 This is a schematic diagram of a power system test model under large-scale grid connection of new energy sources provided by an exemplary embodiment of the present invention; Figure 6 This is a schematic diagram of the change curve of deep peak shaving control quantity and coal consumption of thermal power unit provided in an exemplary embodiment of the present invention; Figure 7 This is a power grid stability provided by an exemplary embodiment of the present invention. Comparison diagram; Figure 8 This is a schematic diagram comparing peak-shaving step responses provided by an exemplary embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of a deep peak-shaving optimization control device for thermal power units under large-scale grid connection conditions provided by an exemplary embodiment of the present invention; Figure 10This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0025] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0026] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0027] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0028] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0029] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0030] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0031] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0032] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0033] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0034] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0035] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0036] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0037] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0038] Exemplary methods Figure 1 This is a flowchart illustrating a deep peak-shaving optimization control method for thermal power units under large-scale grid-connected conditions, provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as... Figure 1 As shown, the deep peak-shaving optimization control method 100 for thermal power units under large-scale grid connection conditions includes the following steps: Step 101: Build a large-scale grid-connected power system model that includes thermal power units, wind power generation units and photovoltaic power generation units, and based on the power system model, construct an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function. Step 102: Using the differential evolution algorithm, the fitness function is constructed by combining the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function. The output scheme of each power generation unit including thermal power units is optimized and solved to obtain the optimal output of thermal power units during deep peak shaving. Step 103: Monitor the current power generation of the thermal power unit in real time and calculate the deviation between the current power generation and the optimal output. Step 104: Input the deviation to the neural network PID controller. The neural network PID controller tunes the proportional, integral, and derivative coefficients online according to the input state variables and calculates the operating control quantities required for the thermal power unit to achieve optimal output. Step 105: Send the operating control quantity to the actuator of the thermal power unit to adjust the actual output of the thermal power unit and complete the deep peak shaving optimization control.

[0039] Specifically, the primary frequency regulation capability of generating units deteriorates significantly under low-load conditions, with a decrease in regulation rate and a 2-3 fold increase in dynamic response time, severely restricting the grid's frequency recovery capability. However, existing research mainly focuses on frequency regulation characteristics under conventional loads, lacking quantitative assessment and optimization of the primary frequency regulation capability of generating units under deep peak-shaving conditions. Optimizing load allocation schemes can effectively reduce the frequency regulation burden of thermal power units and improve system frequency stability. Therefore, this paper proposes a load optimization allocation method considering frequency security under deep peak-shaving conditions to reduce the regulation pressure on generating units and maintain the safe and stable operation of the power grid.

[0040] This invention provides a load optimization allocation method considering frequency security under deep peak shaving. It aims to optimize the load allocation scheme of thermal power units to address the frequency security and stability issues under current deep peak shaving conditions, and solve the problem of insufficient active power regulation capacity of the system. Considering the impact of deep peak shaving on frequency regulation capacity and stable system frequency operation, a dynamic evaluation model integrating multiple deep peak shaving parameters is constructed based on active power regulation amplitude indicators such as peak value and steady-state value, and active power regulation speed indicators such as curve rise time. Furthermore, an optimization model for the primary frequency regulation capacity of deep peak shaving units is constructed, and an optimization model considering primary frequency regulation capacity constraints is proposed for load allocation under deep peak shaving.

[0041] This invention provides a method for deep peak shaving optimization control of thermal power units under large-scale grid connection conditions, with reference to... Figure 2 As shown, the method includes the following steps: Step 1: Build a large-scale grid-connected power system model In this invention, a power system structure model is established based on the conditions of large-scale grid connection of new energy sources, as follows: Figure 3 As shown.

[0042] exist Figure 3 In the power system structure model, thermal power units are the main source of electricity supply, installed at the grid inlet side, and balance the fluctuations in renewable energy access through peak shaving (adjusting output to meet the grid's power demand during off-peak or peak periods). Their output model needs to complement the intermittent characteristics of wind and solar power generation. The output models of each power supply unit under large-scale grid connection are as follows: (1) (2) (3) In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , The photovoltaic panel's operating temperature and reference temperature represent time t.

[0043] Step 2: Quantitative assessment of power grid stability and carrying capacity Step 2.1: Upper-level new energy carrying capacity assessment function New energy carrying capacity refers to the maximum extent to which a power system can continuously and efficiently accept and absorb new energy power generation capacity (wind power and photovoltaic) under the premise of ensuring safe and stable operation. It can be described by the following formula.

[0044] (4) In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. Step 2.2: Lower-level power grid stability assessment function Power grid stability Due to frequency deviation and voltage deviation It consists of two parts, reflecting the fluctuations in the power system during peak shaving.

[0045] (5) (6) (7) In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

[0046] Step 3: Differential Evolutionary Algorithm for Deep Peak Shaving Output Optimization Differential evolution algorithm is a stochastic search optimization algorithm based on swarm intelligence. This algorithm is used to find the optimal solution from the power output schemes of candidate power generation units. Each solution is represented as... , This represents the number of power generation units.

[0047] Throughout the process, the fitness function is constructed as follows: (8) In the formula, Representing the One solution The fitness function of (output scheme); , Representing the One solution The corresponding evaluation function values ​​for the upper and lower layers (output scheme); , This represents the evaluation function of the upper and lower layers.

[0048] After solving the above process, the optimal output of the thermal power generating unit during deep peak shaving is obtained, denoted as . .

[0049] Step 4: Based on the peak-shaving output optimization results, implement the operation control of the thermal power unit. To this end, a control model is designed based on a neural network proportional-integral-derivative (PID) controller. The model structure is as follows: Figure 4 As shown.

[0050] In this control model, the current generating power of the thermal power unit needs to be monitored in real time, denoted as . Then, compared with the optimal output of thermal power generating units during deep peak shaving obtained in the previous chapter. Perform the difference calculation, that is (9) In the formula, Represents real-time power generation and optimal output. The deviation between them.

[0051] Step 5: The input is fed into the neural network PID controller, and through proportional, integral, and derivative calculations, the operating control quantities of the thermal power unit required to achieve the deep peak shaving target are obtained.

[0052] (10) In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and power generation capacity. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , These represent the coefficients of the proportional, integral, and derivative components after neural network optimization. The process for obtaining the coefficients of the proportional, integral, and derivative components after neural network optimization is as follows: (1) Input the state variables of the thermal power unit This includes output deviation, deviation change rate, and historical control parameters.

[0053] (2) Through nonlinear activation function Calculate the hidden layer output ,Right now: (11) In the formula, , This represents the weights and biases of the hidden layer network.

[0054] (3) According to Calculate the output of the output layer, that is , , .

[0055] (12) (13) (14) In the formula, , , These represent the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

[0056] Step 6: [The sentence is incomplete and requires more context to be translated accurately.] Real-time thermal power unit operation control quantity The signal is sent to the actuator of the thermal power unit, which can adjust the power generation capacity, and the deep peak shaving optimization control action of the thermal power unit is completed through the actuator.

[0057] In a specific embodiment of the present invention, to verify the effectiveness of the invention, the IEEE 33-bus system is used as the basis for the calculation, the proportion of renewable energy installed capacity is increased, and a power system test model suitable for algorithm verification under the scenario of large-scale grid connection of renewable energy is constructed. The structural diagram is as follows. Figure 5 As shown.

[0058] Figure 5 The power system shown has three thermal power units (2×600MW supercritical units + 1×300MW subcritical units), one photovoltaic power station and one wind turbine unit connected to it. The parameter configuration is shown in Table 1 below.

[0059] Table 1 Power System Test Model Parameter Configuration

[0060] To simulate the dynamic changes in the real-world power grid environment, a typical anti-peak-shaving day scenario is set up, as shown in Table 2 below.

[0061] Table 2 Typical Scenario Settings

[0062] Based on the proposed deep peak-shaving output optimization method, the differential evolution algorithm is used to optimize the power output. Figure 1 Deep peak-shaving output optimization was performed on a typical anti-peak-shaving day scenario for a large-scale grid-connected power system of new energy sources. The results are shown in Table 3 below.

[0063] Table 3 Optimization results of deep peak shaving output (unit: MW)

[0064] Note: (D) indicates that the unit is currently in a deep peak shaving state, with its output lower than its normal minimum technical output (40% of rated capacity).

[0065] Using the expected output of the three thermal power units (2×600MW supercritical units + 1×300MW subcritical unit) in Table 3, the difference between this expected output and the current real-time monitored power generation of the thermal power units is calculated. This difference is then used as input to calculate the required thermal power unit operation control quantities to achieve the deep peak shaving target, thereby realizing deep peak shaving control of the thermal power units. The deep peak shaving control quantities of the thermal power units are as follows: Figure 6 As shown.

[0066] from Figure 6 As can be seen, in the face of a typical anti-peak day scenario, the deep peak-shaving control quantities (coal consumption variation characteristics) of the two 600MW supercritical units and one 300MW subcritical unit are as follows: During peak load periods (8:00-20:00), all three units jointly increase coal consumption; during off-peak load periods (0:00-4:00, 22:00-24:00), all three units jointly reduce coal consumption. This indicates that the optimized control system coordinates and uniformly schedules the units, jointly responding to changes in net load. Furthermore, throughout the day, the coal consumption of the two 600MW supercritical units is consistently higher than that of the 300MW subcritical unit, especially during the peak load period (14:00-16:00), where the 300MW subcritical unit plays more of a "regulator" role, reducing coal consumption even further when output needs to be reduced, and increasing coal consumption more slowly when output needs to be increased.

[0067] according to Figure 6 Deep peak shaving was achieved, and then the grid stability was monitored during the peak shaving process to verify the peak shaving effect and compare it with three traditional methods. The results are as follows. Figure 7 As shown.

[0068] from Figure 7 As can be seen from the results, under the application of the studied method, the stability of the power grid... ∈[0.90,1.00], while the power grid stability of the other three methods The overall values ​​are all below this figure. A value of <0.90 indicates that the peak-shaving effect of the studied method is better. This is due to the strong response capability of the studied method, which can quickly adjust the control quantity to cope with the load fluctuation problem after the new energy is connected to the grid.

[0069] Faced with a sharp drop in photovoltaic power output, the demand for thermal power units surged from 10MW to 40MW to fill the gap. In response to this situation, the deep peak-shaving step response of thermal power units is as follows: Figure 8 As shown.

[0070] from Figure 8As can be seen, the method studied completes deep peak shaving within 3 seconds and quickly reaches a stable level, while the other three methods require a longer time to complete deep peak shaving. For example, the adaptive peak shaving control method based on the load change rate requires about 5 seconds, the peak shaving control strategy based on the peak shaving surplus coefficient requires about 4 seconds, and the peak shaving control method based on the Cplex solver requires about 6 seconds. This shows that the method studied can quickly respond to rapid load changes or sudden operating conditions, and can make a timely deep peak shaving response, thus having a better peak shaving effect.

[0071] Therefore, this invention proposes a deep peak-shaving optimization control method for thermal power units under large-scale grid-connected conditions. It integrates a two-layer evaluation function into the algorithm's fitness function and solves the optimal output plan through swarm intelligence search, effectively overcoming the limitation of "local optima" in traditional peak-shaving strategies. This ensures that the output of thermal power units can match the fluctuations in renewable energy while also considering their own operational economy and safety. By calculating the deviation between the actual output and the optimal output of the thermal power units in real time, the nonlinear fitting capability of neural networks is used to dynamically optimize the PID parameters, achieving rapid adjustment of the control quantity. Experimental results verify the effectiveness of the method: the grid stability on typical anti-peak-shaving days exceeds 0.90, and the unit step response time under sudden operating conditions is ≤3 seconds, far faster than traditional methods, achieving the dual goals of grid safety and thermal power unit economy.

[0072] Exemplary device Figure 9 This is a schematic diagram of the structure of a deep peak-shaving optimization control device for thermal power units under large-scale grid-connected conditions, provided by an exemplary embodiment of the present invention. Figure 9 As shown, the device 900 includes: Module 910 is used to build a large-scale grid-connected power system model that includes thermal power units, wind power generation units and photovoltaic power generation units, and based on the power system model, to build an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function. The solution module 920 is used to optimize the output scheme of each power generation unit including thermal power units by employing the differential evolution algorithm, which uses the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function to form a fitness function, thereby obtaining the optimal output of thermal power units during deep peak shaving. The first calculation module 930 is used to monitor the current power generation of the thermal power unit in real time and calculate the deviation between the current power generation and the optimal output. The second calculation module 940 is used to input the deviation to the neural network PID controller. The neural network PID controller tunes the proportional, integral, and derivative coefficients online according to the input state variables and calculates the operating control quantities required for the thermal power unit to achieve optimal output. The control module 950 is used to send the operating control quantity to the actuator of the thermal power unit to adjust the actual output of the thermal power unit and complete the deep peak shaving optimization control.

[0073] Optionally, the processing model expression for each power supply unit in the power system model is as follows: In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , Representative moment t The operating temperature and reference temperature of the photovoltaic panel.

[0074] Optionally, the expression for the upper-level new energy carrying capacity assessment function is: In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. The expression for the lower-level power grid stability assessment function is: in, In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

[0075] Optionally, the fitness function can be expressed as: In the formula, Representing the One solution The fitness function; , Representing the One solution The corresponding upper and lower level evaluation function values; , This represents the evaluation function of the upper and lower layers.

[0076] Optionally, the expression for the operation control variable is: In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and power generation capacity. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , The coefficients representing the proportional, integral, and derivative of the optimized neural network; Represents real-time power generation and optimal output. The deviation between them.

[0077] Optionally, the neural network PID controller is tuned online based on the input state variables, including: Input the state variables of the thermal power unit into the neural network PID controller State variables include output deviation, deviation change rate, and historical control variables; Based on state variables, through a nonlinear activation function Calculate the hidden layer output : In the formula, , This represents the weights and biases of the hidden layer network.

[0078] Based on the hidden layer output Calculate the output of the output layer, that is , , .

[0079] In the formula, , , These represent the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

[0080] Exemplary electronic devices Figure 10 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 10 As shown, the electronic device 100 includes one or more processors 101 and memory 102.

[0081] The processor 101 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0082] The memory 102 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 101 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 103 and an output device 104, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0083] In addition, the input device 103 may also include, for example, a keyboard, a mouse, etc.

[0084] The output device 104 can output various information to the outside. The output device 104 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0085] Of course, for the sake of simplicity, Figure 10 Only some of the components of this electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0086] Exemplary computer program products and computer-readable storage media In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0087] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0088] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0089] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0090] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0091] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0092] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0093] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0094] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0095] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for deep peak shaving optimization control of thermal power units under large-scale grid connection conditions, characterized in that, include: A large-scale grid-connected power system model including thermal power units, wind power generation units, and photovoltaic power generation units is constructed. Based on the power system model, an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function are constructed. The differential evolution algorithm is used to optimize the output scheme of each power generation unit containing the thermal power unit by using the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function to form a fitness function, thereby obtaining the optimal output of the thermal power unit during deep peak shaving. The current power generation of the thermal power unit is monitored in real time, and the deviation between the current power generation and the optimal output is calculated. The deviation is input to the neural network PID controller, which tunes the proportional, integral, and derivative coefficients online based on the input state variables and calculates the operating control quantities required for the thermal power unit to achieve the optimal output. The operation control quantity is sent to the actuator of the thermal power unit to adjust the actual output of the thermal power unit and complete the deep peak shaving optimization control.

2. The method according to claim 1, characterized in that, The processing model expressions for each power supply unit in the power system model are as follows: In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , Representative moment t The operating temperature and reference temperature of the photovoltaic panel.

3. The method according to claim 1, characterized in that, The expression for the upper-level new energy carrying capacity assessment function is as follows: In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. The expression for the lower-level power grid stability assessment function is as follows: in, In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

4. The method according to claim 3, characterized in that, The expression for the fitness function is: In the formula, Representing the One solution The fitness function; , Representing the One solution The corresponding upper and lower level evaluation function values; , This represents the evaluation function of the upper and lower layers.

5. The method according to claim 1, characterized in that, The expression for the operational control quantity is: In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and output. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , The coefficients representing the proportional, integral, and derivative of the optimized neural network; Represents real-time power generation and optimal output. The deviation between them.

6. The method according to claim 5, characterized in that, The neural network PID controller is tuned online based on the input state variables, including: The state variables of the thermal power unit are input into the neural network PID controller. The state variables include output deviation, deviation change rate, and historical control variables; Based on the state variables, a nonlinear activation function is used. Calculate the hidden layer output : In the formula, , This represents the weights and biases of the hidden layer network. According to the output of the hidden layer Calculate the output of the output layer, that is , , . In the formula, , , This represents the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

7. A deep peak-shaving optimization control device for thermal power units under large-scale grid connection conditions, characterized in that, include: The module is used to build a large-scale grid-connected power system model that includes thermal power units, wind power generation units and photovoltaic power generation units, and based on the power system model, to build an upper-level new energy carrying capacity assessment function and a lower-level power grid stability assessment function. The solution module is used to optimize the output scheme of each power generation unit containing the thermal power unit by employing a differential evolution algorithm, using the upper-level new energy carrying capacity assessment function and the lower-level power grid stability assessment function together to form a fitness function, so as to obtain the optimal output of the thermal power unit during deep peak shaving. The first calculation module is used to monitor the current power generation of the thermal power unit in real time and calculate the deviation between the current power generation and the optimal output. The second calculation module is used to input the deviation to the neural network PID controller. The neural network PID controller tunes the proportional, integral, and derivative coefficients online according to the input state variables and calculates the operating control quantities required by the thermal power unit to achieve the optimal output. The control module is used to send the operation control quantity to the actuator of the thermal power unit to adjust the actual output of the thermal power unit and complete the deep peak shaving optimization control.

8. The apparatus according to claim 7, characterized in that, The processing model expressions for each power supply unit in the power system model are as follows: In the formula, represent The thermal power unit output at all times; This indicates the start / stop status of the unit (1 for running, 0 for stopped). Represents the load factor; Minimum technical output; Represents rated power; This represents the rated output of the wind turbine. , , Represents cut-in wind speed, cut-out wind speed, and rated wind speed; represent Wind speed at all times; represent Wind turbine output at all times; represent The actual output power of the photovoltaic unit at any given time; Represents the rated power under standard test conditions; , represent Actual solar irradiance at any given time, and reference irradiance under standard test conditions; Represents the temperature coefficient; , Representative moment t The operating temperature and reference temperature of the photovoltaic panel.

9. The apparatus according to claim 7, characterized in that, The expression for the upper-level new energy carrying capacity assessment function is as follows: In the formula, represent The capacity to carry new energy at all times; , represent Time Node Solar and wind power in Power absorption at any given time; , This represents the set of nodes containing photovoltaic power and the set of nodes containing wind power. The expression for the lower-level power grid stability assessment function is as follows: in, In the formula, represent The system frequency at that moment; Represents the rated frequency; represent thermal power units Actual output; Represents thermal power units Reference output; , Represents the weighting coefficient; , Represents the upper and lower limits of the voltage at node k; represent Time Node The voltage amplitude; Represents reactive power compensation equipment The output; This represents the number of reactive power compensation devices.

10. The apparatus according to claim 9, characterized in that, The expression for the fitness function is: In the formula, Representing the One solution The fitness function; , Representing the One solution The corresponding upper and lower level evaluation function values; , This represents the evaluation function of the upper and lower layers.

11. The apparatus according to claim 7, characterized in that, The expression for the operational control quantity is: In the formula, represent The control parameters for thermal power unit operation at all times are: coal consumption and output. The greater the coal consumption, the higher the power generation capacity of the thermal power unit. , , The coefficients representing the proportional, integral, and derivative of the optimized neural network; Represents real-time power generation and optimal output. The deviation between them.

12. The apparatus according to claim 11, characterized in that, The neural network PID controller is tuned online based on the input state variables, including: The state variables of the thermal power unit are input into the neural network PID controller. The state variables include output deviation, deviation change rate, and historical control variables; Based on the state variables, a nonlinear activation function is used. Calculate the hidden layer output : In the formula, , This represents the weights and biases of the hidden layer network. According to the output of the hidden layer Calculate the output of the output layer, that is , , . In the formula, , , This represents the PID parameters before optimization; , , , , This represents the weights and biases of the output layer.

13. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-6.

14. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-6.

Images