CN-122026379-A - Dynamic load distribution method and related device for thermal power plant

CN122026379ACN 122026379 ACN122026379 ACN 122026379ACN-122026379-A

Abstract

The application belongs to a thermal power plant allocation method, and provides a thermal power plant load dynamic allocation method and a related device, aiming at the technical problems that the existing thermal power plant load allocation model has the defects of neglecting unit response delay, fixed adjustment period and multi-source uncertainty coping, by acquiring static parameters, dynamic response parameters, real-time and uncertainty data of a thermal power plant and dynamically constructing modeling parameters, combining with an objective function integrating economy, environmental protection, smoothness adjustment and multi-source uncertainty cost, adopting an improved self-adaptive multi-objective quantum genetic algorithm solution model, and realizing optimization and upgrading of thermal power plant load allocation from multiple dimensions. According to the method, by means of the design of the adjustment smoothness in the objective function and the cooperation of the follow-up extendable freezing period constraint, frequent instructions of load adjustment are effectively reduced, and the operation intensity of operators is greatly reduced. The multi-objective collaborative optimization is realized by integrating the economical efficiency, the environmental protection and the uncertainty into the objective function according to the requirements.

Inventors

ZHANG JISHUN
ZHU JINGWEI
CHAI SHENGKAI
WU TAO
DU BAOHUA
WU ZHIQUN

Assignees

西安西热电站信息技术有限公司
西安热工研究院有限公司

Dates

Publication Date: 20260512
Application Date: 20260119

Claims (10)

1. A method for dynamically distributing load of a thermal power plant, comprising: Acquiring static parameters, dynamic response parameters and real-time and uncertainty data of a thermal power generating unit as acquired data; Dynamically constructing parameters for modeling according to the acquired data; According to the acquired data and parameters for modeling, constructing a load dynamic distribution model of the thermal power plant, wherein an objective function of the load dynamic distribution model of the thermal power plant fuses economy, environmental protection, adjustment smoothness and multi-source uncertainty cost; And solving a load dynamic distribution model of the thermal power plant by adopting an improved self-adaptive multi-target quantum genetic algorithm to obtain a load dynamic distribution result of the thermal power plant, wherein the improved self-adaptive multi-target quantum genetic algorithm improves the convergence rate by dynamically adjusting a quantum bit revolving door strategy.
2. The method for dynamically distributing load of thermal power plant according to claim 1, wherein after obtaining the dynamic distribution result of load of thermal power plant, further comprises: the load, uncertainty factors and operation parameters of the thermal power generating unit are monitored in real time and used as monitoring data; Based on the monitoring data, calculating response progress, uncertainty influence and distribution scheme deviation by using a data mining algorithm, and if the response progress, uncertainty influence and distribution scheme deviation exceed a preset condition, taking the current thermal power unit as new acquired data, and carrying out dynamic distribution again.
3. The method for dynamically distributing load of thermal power plant according to claim 1, wherein the objective function of the dynamic distribution model of load of thermal power plant comprises: Wherein, the To blend the cost of economy, environmental protection, adjustment smoothness and multi-source uncertainty, In order to optimize the starting moment of the cycle, For the duration of a single adjustment period, As a function of the coal consumption, Is the output of the ith thermal power generating unit at the time t, Is the weight coefficient of the environmental protection, As a function of the discharge, Is the first The cost factor of the uncertainty factor is the seed, The index is quantified for the uncertainty factor, In order to adjust the smoothness penalty coefficient, Is the first The output force adjustment quantity of the ith thermal power generating unit in the period, In order to adjust the consistency penalty factor, Is the first The average value of the adjustment quantity of the thermal power generating unit in the period, As a total number of cycles, Is the number of thermal power generating units.
4. A thermal power plant load dynamic distribution method according to claim 3, wherein the constraint condition of the thermal power plant load dynamic distribution model comprises: The method comprises the following steps of output upper and lower limit constraint, environment-friendly limit constraint, dynamic adjustment period constraint, self-adaptive ladder adjustment constraint, multi-source prediction compensation constraint, freezing period strengthening constraint and risk constraint.
5. The method for dynamically distributing load of thermal power plant according to claim 1, wherein dynamically constructing parameters for modeling according to the acquired data comprises: setting a dynamic adjustment period, dynamically adapting single maximum adjustment amount and optimizing parameters in a self-adaptive way.
6. The method for dynamically distributing load of a thermal power plant according to claim 5, wherein the method for solving the dynamic distribution model of the load of the thermal power plant by adopting the improved self-adaptive multi-objective quantum genetic algorithm to obtain the dynamic distribution result of the load of the thermal power plant comprises the following steps: When the load dynamic distribution model of the thermal power plant is solved and output, the optimal load dynamic distribution result of the thermal power plant is decomposed into a plurality of alphabet sequences, and each sub-target sequence corresponds to an adjustment period, a freezing period and an uncertainty response strategy.
7. The dynamic load distribution method for the thermal power plant according to claim 6, wherein: The dynamic adjustment period setting comprises the steps of determining an adjustment period by adopting Monte Carlo simulation based on probability distribution of historical response time of the thermal power unit; the single maximum adjustment amount is dynamically adjusted by combining the real-time load, coal quality and power grid fluctuation state of the thermal power unit through a fuzzy reasoning system; The parameter self-adaptive optimization comprises optimizing parameters of a freezing period and a smoothness penalty coefficient by using a reinforcement learning algorithm.
8. A thermal power plant load dynamic distribution system, comprising: the data module is used for acquiring static parameters, dynamic response parameters and real-time and uncertainty data of the thermal power generating unit as acquired data; The parameter module is used for dynamically constructing parameters for modeling according to the acquired data; The system comprises a model construction module, a model analysis module and a model analysis module, wherein the model construction module is used for constructing a thermal power plant load dynamic distribution model according to acquired data and parameters for modeling; The distribution module is used for solving a load dynamic distribution model of the thermal power plant by adopting an improved self-adaptive multi-target quantum genetic algorithm to obtain a load dynamic distribution result of the thermal power plant, and the improved self-adaptive multi-target quantum genetic algorithm improves the convergence rate by dynamically adjusting a quantum bit revolving door strategy.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the thermal power plant load dynamic allocation method according to any one of claims 1-7 when the computer program is executed by the processor.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the thermal power plant load dynamic allocation method according to any one of claims 1-7.

Description

Dynamic load distribution method and related device for thermal power plant Technical Field The application belongs to a thermal power plant allocation method, and particularly relates to a thermal power plant load dynamic allocation method and a related device. Background At present, load distribution of a thermal power plant is a core link for balancing power generation efficiency, cost and equipment safety. In the prior art, load distribution models have focused on economy and environmental aspects such as coal consumption minimization and pollutant emission control. However, the method still has significant limitations in the application process, and is characterized in that the response delay of the unit is ignored, the load of the existing model can be instantaneously adjusted, so that the instruction frequently changes and exceeds the operation capacity of operators, the adjustment period is fixed and is not linked with the actual response characteristic of the unit, the multi-source uncertainty is insufficient in response, and the deviation between the distribution result and the actual demand is large. Disclosure of Invention Aiming at the technical problems that the conventional load distribution model of the thermal power plant ignores the response delay, the fixed adjustment period and the insufficient multi-source uncertainty coping, the application provides a dynamic load distribution method and a related device of the thermal power plant. In order to achieve the above purpose, the application is realized by adopting the following technical scheme: in a first aspect, the present application provides a method for dynamically distributing load of a thermal power plant, including: Acquiring static parameters, dynamic response parameters and real-time and uncertainty data of a thermal power generating unit as acquired data; Dynamically constructing parameters for modeling according to the acquired data; According to the acquired data and parameters for modeling, constructing a load dynamic distribution model of the thermal power plant, wherein an objective function of the load dynamic distribution model of the thermal power plant fuses economy, environmental protection, adjustment smoothness and multi-source uncertainty cost; And solving a load dynamic distribution model of the thermal power plant by adopting an improved self-adaptive multi-target quantum genetic algorithm to obtain a load dynamic distribution result of the thermal power plant, wherein the improved self-adaptive multi-target quantum genetic algorithm improves the convergence rate by dynamically adjusting a quantum bit revolving door strategy. Further, after the dynamic load distribution result of the thermal power plant is obtained, the method further comprises: the load, uncertainty factors and operation parameters of the thermal power generating unit are monitored in real time and used as monitoring data; Based on the monitoring data, calculating response progress, uncertainty influence and distribution scheme deviation by using a data mining algorithm, and if the response progress, uncertainty influence and distribution scheme deviation exceed a preset condition, taking the current thermal power unit as new acquired data, and carrying out dynamic distribution again. Further, the objective function of the dynamic load distribution model of the thermal power plant comprises: Wherein, the To blend the cost of economy, environmental protection, adjustment smoothness and multi-source uncertainty,In order to optimize the starting moment of the cycle,For the duration of a single adjustment period,As a function of the coal consumption,Is the output of the ith thermal power generating unit at the time t,Is the weight coefficient of the environmental protection,As a function of the discharge,Is the firstThe cost factor of the uncertainty factor is the seed,The index is quantified for the uncertainty factor,In order to adjust the smoothness penalty coefficient,Is the firstThe output force adjustment quantity of the ith thermal power generating unit in the period,In order to adjust the consistency penalty factor,Is the firstThe average value of the adjustment quantity of the thermal power generating unit in the period,As a total number of cycles,Is the number of thermal power generating units. Further, the constraint conditions of the dynamic load distribution model of the thermal power plant comprise: The method comprises the following steps of output upper and lower limit constraint, environment-friendly limit constraint, dynamic adjustment period constraint, self-adaptive ladder adjustment constraint, multi-source prediction compensation constraint, freezing period strengthening constraint and risk constraint. Further, the dynamically constructing parameters for modeling according to the acquired data includes: setting a dynamic adjustment period, dynamically adapting single maximum adjustment amount and optimizing parameters in a self