CN-121332754-B - Active regulation and control method and system for load interaction of coal-fired unit and power grid

CN121332754BCN 121332754 BCN121332754 BCN 121332754BCN-121332754-B

Abstract

The embodiment of the invention relates to the technical field of coal-fired units, in particular to an active regulation and control method and system for load interaction of a coal-fired unit and a power grid. The method comprises the steps of determining target load power and load adjustment time of a coal-fired unit according to fluctuation amplitude, a prediction time point for generating the fluctuation amplitude, maximum climbing speed, upward standby capacity and downward standby capacity of the coal-fired unit if the fluctuation amplitude of power grid load power is predicted to be larger than a preset amplitude threshold through a load power prediction model, sending the target load power and the load adjustment time to the coal-fired unit, determining electric heating power of a thick-wall part according to the target load power and the load adjustment time by the coal-fired unit, and heating the outer wall of the thick-wall part according to the electric heating power and a preset electric heating algorithm to reduce the temperature difference between the inner wall and the outer wall of the thick-wall part so as to cope with the fluctuation amplitude. The technical scheme of the invention can improve the regulation and control capability of the coal-fired unit and the power grid when coping with load fluctuation.

Inventors

PANG LIPING
LI SIYU
LI JIANGPING
YU PENGFENG
HE JIANLE
ZHANG PENGWEI
HUANG YONGCHEN
Lv Buchu
SHI XUETONG

Assignees

华北电力大学

Dates

Publication Date: 20260508
Application Date: 20251024

Claims (9)

1. An active regulation and control method for interaction between a coal-fired unit and a power grid load is applied to an active regulation and control system for interaction between the coal-fired unit and the power grid load, and the system comprises the power grid and the coal-fired unit and is characterized by comprising the following steps: If the power grid predicts that the fluctuation amplitude of the power grid load power is larger than a preset amplitude threshold value through a trained load power prediction model, determining target load power and load adjustment time of the coal-fired unit according to the fluctuation amplitude, a prediction time point for generating the fluctuation amplitude, the maximum climbing rate, upward standby capacity and downward standby capacity of the coal-fired unit, and sending the target load power and load adjustment time to the coal-fired unit; Determining the electric heating power of the thick-wall part of the coal-fired unit through a feedforward-feedback composite control algorithm according to the target load power and the load adjustment time by the coal-fired unit; Heating the outer wall of the thick-wall part in advance by the coal-fired unit according to the electric heating power and a preset electric heating algorithm so as to cope with the fluctuation range by reducing the temperature difference between the inner wall and the outer wall of the thick-wall part; The method for determining the electric heating power of the thick-wall part of the coal-fired unit through a feedforward-feedback composite control algorithm according to the target load power and the load adjustment time comprises the following steps: determining a target temperature value of the thick-wall component according to the target load power and the load adjustment time by the following formula: Wherein, the Is that The target temperature value at the moment in time, For the initial temperature value of the thick-walled component, As a function of the power of the target load, Adjusting a time function for the load; determining an electrical heating power of the thick-walled component from the target temperature value, the electrical heating power being calculated by the formula: Wherein, the For the purpose of electrically heating up the power, Is the equivalent heat capacity of the thick-walled component, As a coefficient of equivalent heat loss, In order to be at the temperature of the environment, As a function of the dynamic gain, 。
2. The method of claim 1, wherein the training process of the load power prediction model is: According to historical operation data of the power stations in the electricity utilization area of the coal-fired unit; And inputting the power, the load power, the ambient temperature, the ambient humidity, the wind speed, the illumination intensity and the corresponding timestamp information in the historical operation data into a data input layer, training a neural network model, and obtaining a trained load power prediction model, wherein the input of the load power prediction model is timestamp information, the output of the load power prediction model is a predicted load value, and the timestamp information comprises a week number identifier and a holiday identifier.
3. The method of claim 2, wherein the inputting the power, the load power, the ambient temperature, the ambient humidity, the wind speed, the illumination intensity and the corresponding timestamp information in the historical operation data into a data input layer, training a neural network model, and obtaining a trained load power prediction model comprises; Dividing the power, the load power, the ambient temperature, the ambient humidity, the wind speed and the illumination intensity according to time sequences according to the timestamp information to form time sequence data; Inputting the time sequence data to an LSTM network layer, wherein the LSTM network layer comprises at least one LSTM unit; the LSTM unit operates as follows: forgetting door is expressed as The input gate is denoted as The output gate is denoted as , wherein, In order to hide the state at the previous moment, For the current input to be entered, And In order to train the resulting weight values, And In order to train the resulting bias, Activating a function for sigmoid; Transmitting the hidden state of the last layer of the LSTM network to a full-connection layer to obtain a predicted load value at a preset time in the future, , wherein, Is that The predicted load value at the moment in time, For the final hidden state of the LSTM network, And Is a full connection layer parameter.
4. The method of claim 1, wherein said determining a target load power and load adjustment time for said coal-fired unit based on said fluctuation amplitude, a predicted point in time at which said fluctuation amplitude is generated, a maximum ramp rate of said coal-fired unit, an upward backup capacity and a downward backup capacity comprises: determining the target load power according to the fluctuation amplitude, the upward standby capacity and the downward standby capacity of the coal-fired unit by the following formula: Wherein, the For the target load power to be the same, For the current load power to be the current load power, For the amplitude of the wave motion, In order to provide a downward reserve capacity, For upward reserve capacity; Determining the load adjustment time according to the target load power and the maximum climbing rate of the coal-fired unit, and determining the load adjustment time through the following formula: Wherein, the In order to adjust the time for the load, In order to provide a rate of change of power, , Is the maximum climbing rate of the coal-fired unit, In order to reach the predicted point in time, Is a safety factor.
5. The method of claim 1, the heating the outer wall of the thick-walled component according to the electrical heating power and a preset electrical heating algorithm, comprising: the electric heating algorithm is as follows: Wherein, the , In order to calculate the period of time, As a temperature parameter of the thick-walled component, Is at the current time as a parameter The parameter value of the moment and the parameter value of the last sampling period, Is a coefficient of proportionality and is used for the control of the power supply, For electric tracing power An incremental function of the time of day, For the purpose of electrically heating up the power, And the difference value between the target load power and the current load power is obtained.
6. The method as recited in claim 5, further comprising: For a preset period of time And then, determining the actual climbing rate of the coal-fired unit according to the temperature parameters of the thick-wall parts by the following formula: Wherein, the For the actual ramp rate, for the thermal stress determined from the temperature parameters of the thick-walled component, And determining a target climbing rate according to the target load power.
7. An active regulation and control system for the interaction of a coal-fired unit and a power grid load is characterized by comprising a power grid and the coal-fired unit; The power grid is used for predicting that the fluctuation amplitude of the power grid load power is larger than a preset amplitude threshold value through a trained load power prediction model, determining target load power and load adjustment time of the coal-fired unit according to the fluctuation amplitude, a prediction time point for generating the fluctuation amplitude, the maximum climbing rate, upward standby capacity and downward standby capacity of the coal-fired unit, and sending the target load power and load adjustment time to the coal-fired unit; the coal-fired unit is used for determining the electric heating power of the thick-wall part of the coal-fired unit through a feedforward-feedback composite control algorithm according to the target load power and the load adjustment time, and Heating the outer wall of the thick-wall part in advance according to the electric heating power and a preset electric heating algorithm so as to cope with the fluctuation range by reducing the temperature difference between the inner wall and the outer wall of the thick-wall part; the electric heating power is calculated by the following method: determining a target temperature value of the thick-wall component according to the target load power and the load adjustment time by the following formula: Wherein, the Is that The target temperature value at the moment in time, For the initial temperature value of the thick-walled component, As a function of the power of the target load, Adjusting a time function for the load; determining an electrical heating power of the thick-walled component from the target temperature value, the electrical heating power being calculated by the formula: Wherein, the For the purpose of electrically heating up the power, Is the equivalent heat capacity of the thick-walled component, As a coefficient of equivalent heat loss, In order to be at the temperature of the environment, As a function of the dynamic gain, 。
8. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of any of claims 1-6 when the computer program is executed.
9. A computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-6.

Description

Active regulation and control method and system for load interaction of coal-fired unit and power grid Technical Field The invention relates to the technical field of coal-fired units, in particular to an active regulation and control method and system for load interaction of a coal-fired unit and a power grid. Background In an electric power system, the duty ratio of new energy sources such as wind power, photovoltaic and the like is continuously improved, and the output of the new energy sources has the characteristics of high intermittence and high volatility, so that the stable operation of a power grid can be possibly influenced. At present, when the load of the power grid fluctuates, the interaction between the power grid and the coal-fired unit is mainly realized through a power generation control regulation mode. The demand of the power grid to the power grid frequency and the voltage under the power load fluctuation is met through the passive response of the regulation mode, when the power grid load power is larger and fluctuates fast, the heat transfer speed of the thick-wall part in the coal-fired unit is far smaller than the speed of the power grid to the load demand electric signal, so that the response of the coal-fired unit is lagged, the temperature of the inner wall of the thick-wall part rises fast at the moment, the outer wall forms larger temperature difference due to the heat transfer lagging, the service life of equipment can be shortened for a long time, and potential safety hazards are caused. Based on this, there is a need for an active control method and system for interaction between a coal-fired unit and a power grid load to solve the above-mentioned problems. Disclosure of Invention The invention provides an active regulation and control method and an active regulation and control system for load interaction of a coal-fired unit and a power grid, which can improve the interactive regulation and control capability of the coal-fired unit and the power grid when the load fluctuation is faced. In a first aspect, the invention provides an active regulation and control method for interaction between a coal-fired unit and a power grid load, which is applied to an active regulation and control system for interaction between the coal-fired unit and the power grid load, wherein the system comprises a power grid and the coal-fired unit, and comprises the following steps: If the power grid predicts that the fluctuation amplitude of the power grid load power is larger than a preset amplitude threshold value through a trained load power prediction model, determining target load power and load adjustment time of the coal-fired unit according to the fluctuation amplitude, a prediction time point for generating the fluctuation amplitude, the maximum climbing rate, upward standby capacity and downward standby capacity of the coal-fired unit, and sending the target load power and load adjustment time to the coal-fired unit; Determining the electric heating power of the thick-wall part of the coal-fired unit through a feedforward-feedback composite control algorithm according to the target load power and the load adjustment time by the coal-fired unit; And heating the outer wall of the thick-wall part by the coal-fired unit according to the electric heating power and a preset electric heating algorithm for 1-2 hours in advance, so as to cope with the fluctuation range by reducing the temperature difference of the inner wall and the outer wall of the thick-wall part. In a second aspect, the invention provides an active regulation and control system for load interaction of a coal-fired unit and a power grid, wherein the system comprises the power grid and the coal-fired unit; The power grid is used for predicting that the fluctuation amplitude of the power grid load power is larger than a preset amplitude threshold value through a trained load power prediction model, determining target load power and load adjustment time of the coal-fired unit according to the fluctuation amplitude, a prediction time point for generating the fluctuation amplitude, the maximum climbing rate, upward standby capacity and downward standby capacity of the coal-fired unit, and sending the target load power and load adjustment time to the coal-fired unit; the coal-fired unit is used for determining the electric heating power of the thick-wall part of the coal-fired unit through a feedforward-feedback composite control algorithm according to the target load power and the load adjustment time, and And heating the outer wall of the thick-wall part in advance for 1-2 h according to the electric heating power and a preset electric heating algorithm so as to cope with the fluctuation range by reducing the temperature difference between the inner wall and the outer wall of the thick-wall part. In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer