Multi-objective optimization planning method and system for deep peak regulation transformation of thermal power generating unit

Abstract

The invention relates to the technical field of coal-fired power generation, and discloses a thermal power generating unit deep peak regulation transformation multi-objective optimization planning method, which comprises the following steps: step 1, data preprocessing: for uncertainty of system data, data noise and uncertainty can be reduced by adopting a data preprocessing technology, for example, data noise and uncertainty can be reduced; the random fluctuation of the data can be reduced by using technologies such as a filter and a smoothing algorithm; and step 2, algorithm optimization is carried out, selection of a proper optimization algorithm is the key of system optimization, and a multi-objective optimization problem can be solved by using optimization algorithms such as a multi-objective genetic algorithm and a multi-objective particle swarm optimization algorithm. By optimizing the operation strategy and the control system of the thermal power generating unit, the system can respond to the change of the power load more flexibly, and the peak regulation capacity is improved. Therefore, the thermal power generating unit can provide more power supply during the peak period of power demand, so that the power supply reliability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal-fired power generation, and specifically to a multi-objective optimization planning method and system for deep peak shaving transformation of thermal power units. Background Art

[0002] A thermal power unit refers to a generator unit that mainly uses coal as fuel. The capacity of thermal power units has increased from the 200 MW level to the 300 - 600 MW level, and by 1973, the largest thermal power unit reached 1300 MW. Large units and large power plants have greatly improved the thermal efficiency of thermal power generation, and the construction investment and power generation cost per kilowatt have also been continuously reduced. The "three reforms linkage" of coal power is for energy conservation, carbon reduction, heating transformation, and flexibility transformation of coal-fired power units, providing technical support for the new power system and the clean and low-carbon transformation of energy.

[0003] The main problems faced by the multi-objective optimization planning method and system for deep peak shaving transformation of thermal power units are how to achieve the expected deep peak shaving capacity and how to reduce system costs. The requirements for the deep peak shaving capacity of a pure condensing unit include: the load range is between 100 - 20%; without inputting auxiliary energy (such as oil / plasma, etc.) for combustion assistance, it can ensure stable combustion of the boiler, and under the requirement of meeting ultra-low emissions, its minimum stable operation load reaches 20%; the time for the unit to adjust from 50% load to the minimum load does not exceed 1.5 hours, and the time for the unit to adjust from the minimum load to 50% load does not exceed 1 hour. In addition, it is also necessary to consider how to minimize system costs. Achieving these goals requires the comprehensive collaborative efforts of local government authorities, relevant enterprises, and third parties. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a multi-objective optimization planning method and system for deep peak shaving transformation of thermal power units, which solves the problems of how to achieve the expected deep peak shaving capacity and how to reduce system costs.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A multi-objective optimization planning method for deep peak shaving transformation of thermal power units includes the following steps: Step 1, perform data preprocessing. For the uncertainty of system data, data preprocessing techniques can be used to reduce data noise and uncertainty. For example, techniques such as filters and smoothing algorithms can be used to reduce the random fluctuations of data; Step 2, perform algorithm optimization. Selecting a suitable optimization algorithm is the key to optimizing the system. Optimization algorithms such as multi-objective genetic algorithms and multi-objective particle swarm algorithms can be used to solve multi-objective optimization problems. At the same time, methods such as parameter adjustment and heuristic algorithms can be used to improve the efficiency and accuracy of the algorithm; Step 3: Determine the feasible solution set. In multi-objective optimization problems, it is very important to determine the feasible solution set and trade-off factors. Multi-objective decision-making methods can be used to determine the feasible solution set, and the trade-off factors can be adjusted and optimized according to the actual situation. Step 4: Meet the real-time requirements. To meet the real-time requirements, real-time data acquisition and processing technologies can be adopted, and instant control algorithms can be used to quickly respond to the needs of real-time changes. At the same time, reasonable control strategies and scheduling algorithms can be designed to ensure the stability and reliability of the system. Step 5: Create a visualization interface. To facilitate users to adjust parameters and conduct decision-making analysis, a visualization interface can be designed to display the optimization results and the feasible solution set. Through the visualization interface, users can more intuitively understand the system performance and optimization effects, improving the usability and ease of use of the system. Step 6: Determine the goals of the deep peak shaving transformation based on the operating data and load demand of the thermal power unit. Step 7: Establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraint conditions. Step 8: Use an optimization algorithm to solve the model to obtain the optimal deep peak shaving transformation plan.

[0006] Preferably, in Step 7, the objectives considered in the optimization model include improving power generation efficiency, reducing fuel consumption, and controlling emission limits.

[0007] Preferably, in Step 7, the constraint conditions considered in the optimization model include keeping the power generation within a certain range and meeting the environmental emission standards.

[0008] Preferably, in Step 2, during the solution process of the genetic algorithm, genetic operations such as crossover, mutation, and selection are considered. During the iterative process of the genetic algorithm, the fitness function is used to evaluate the quality of each individual to select excellent individuals for reproduction.

[0009] Preferably, in Step 2, during the iterative process of the genetic algorithm, multiple crossover and mutation methods are adopted to increase the diversity of the population and the search space. During the iterative process of the genetic algorithm, an adaptive parameter adjustment strategy is introduced to improve the convergence and search efficiency of the algorithm.

[0010] Preferably, in Step 2, during the iterative process of the genetic algorithm, an elitist strategy is adopted to retain excellent individuals to prevent the search from prematurely falling into a local optimal solution.

[0011] Preferably, in Step 2, during the iterative process of the genetic algorithm, appropriate termination conditions are set, such as reaching the maximum number of iterations or meeting a certain convergence criterion.

[0012] Preferably, in step two, during the solution process of the genetic algorithm, parallel computing technology is adopted to improve the solution efficiency and speed.

[0013] Preferably, in step six, the operation data and load demand of the thermal power unit are obtained in real time through sensors.

[0014] Preferably, a multi-objective optimization planning system for deep peak shaving transformation of thermal power units includes a data acquisition module, an objective determination module, an optimization model establishment module, and an optimization solution module. The data acquisition module is used to obtain the operation data and load demand of the thermal power unit. The objective determination module is used to determine the objectives of the deep peak shaving transformation according to the operation data and load demand. The optimization model establishment module is used to establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraint conditions. The optimization solution module is used to solve the model using an optimization algorithm to obtain the optimal deep peak shaving transformation plan.

[0015] Preferably, the optimization model establishment module consists of an efficiency unit, an operating cost unit, and an emission limit unit. The efficiency unit converts the input energy or resources into useful outputs while minimizing energy or resource losses as much as possible. The design and optimization of the efficiency unit aim to improve the overall efficiency and performance of the system. The operating cost unit is a component in a system, device, or process, and its main function is to calculate and manage the costs during the operation process. The design and optimization of the operating cost unit aim to reduce the operating cost of the system, improve efficiency and economy. The emission limit unit is a component in a system, device, or process, and its main function is to monitor and control the emissions of pollutants to meet relevant environmental regulations and standards.

[0016] Preferably, the optimization solution module consists of a genetic algorithm unit, an ant colony algorithm unit, a simulated annealing algorithm unit, and a particle swarm algorithm unit. The genetic algorithm unit is an optimization algorithm that simulates the natural evolution process and searches for the optimal solution to the problem by simulating operations such as gene inheritance, crossover, and mutation. The ant colony algorithm unit is an optimization algorithm that simulates the behavior of ants searching for food and information transfer, and searches for the optimal solution to the problem by simulating the behavior rules and information transfer of ants when solving problems. The simulated annealing algorithm unit is a global optimization algorithm based on random search. By simulating the annealing process in metal smelting, it accepts inferior solutions with a certain probability to jump out of the local optimal solution and search for the global optimal solution. The particle swarm algorithm unit is an optimization algorithm that simulates the group behavior of bird flocks or fish schools and searches for the optimal solution through cooperation and information exchange among individuals.

[0017] Working principle: First, determine multiple objectives, such as improving the peak shaving capacity of the power grid, reducing fuel consumption, and increasing power generation efficiency. Collect the operating data of thermal power units, including power load demand, fuel price, and unit operating parameters. Based on the collected data, establish an optimization model for the deep peak shaving transformation of thermal power units. The model includes an objective function and constraints. Apply multi-objective optimization algorithms, such as genetic algorithms and particle swarm algorithms, to solve the model. By continuously iterating and adjusting parameters, find the optimal solution set, that is, the Pareto optimal solution set. Evaluate the obtained Pareto optimal solution set, and select the optimal solution according to actual requirements and priorities. According to the selected optimal solution, perform a deep peak shaving transformation on the thermal power unit. This may involve adjusting the unit's operating strategy, optimizing the unit's control system, and updating key equipment. After the transformation is completed, monitor and optimize the thermal power unit, and continuously adjust and optimize the unit's operating strategy according to the actual operating conditions to achieve the goal of deep peak shaving.

[0018] The present invention provides a multi-objective optimization planning method and system for the deep peak shaving transformation of thermal power units. It has the following beneficial effects: By optimizing the operating strategy and control system of the thermal power unit, the system can respond more flexibly to changes in power load and improve the peak shaving capacity. This can enable the thermal power unit to provide more power supply during peak power demand periods, thereby improving power supply reliability.

[0019] By optimizing the operating parameters and control strategies of the thermal power unit, the system can reduce fuel consumption. This can reduce fuel costs and improve the economy of the thermal power unit.

[0020] By optimizing the operating parameters and control strategies of the thermal power unit, the system can increase power generation efficiency, which can reduce energy waste and improve the energy utilization rate of the thermal power unit.

[0021] By optimizing the operating strategy and control system of the thermal power unit, the system can improve the reliability of the thermal power unit, which can reduce unit failures and downtime and improve the stability and reliability of power supply.

[0022] Through multi-objective optimization planning, the system can maximize the utilization of the resources of the thermal power unit on the premise of meeting the power load demand. This can improve resource utilization efficiency and reduce resource waste. Brief Description of the Drawings

[0023] Figure 1 It is the flow chart of the thermal power unit transformation system of the present invention; Figure 2 It is the flow chart of the optimization model establishment module of the present invention; Figure 3 It is the flow chart of the optimization solution module of the present invention. Specific embodiments

[0024] The following will describe in clear and complete detail the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0025] Please refer to the attached Figure 1 - attached Figure 3 , the embodiments of the present invention provide a multi-objective optimization planning method for deep peak shaving transformation of thermal power units, including the following steps: Step 1, perform data preprocessing. For the uncertainty of system data, data preprocessing techniques can be used to reduce data noise and uncertainty. For example, techniques such as filters and smoothing algorithms can be used to reduce the random fluctuations of data; Step 2, perform algorithm optimization. Selecting a suitable optimization algorithm is the key to optimizing the system. Optimization algorithms such as multi-objective genetic algorithms and multi-objective particle swarm algorithms can be used to solve multi-objective optimization problems. At the same time, methods such as parameter adjustment and heuristic algorithms can be used to improve the efficiency and accuracy of the algorithm; Step 3, determine the feasible solution set. In multi-objective optimization problems, it is very important to determine the feasible solution set and trade-off factors. Multi-objective decision-making methods can be used to determine the feasible solution set, and at the same time, the trade-off factors can be adjusted and optimized according to the actual situation; Step 4, meet the real-time requirements. In order to meet the real-time requirements, real-time data acquisition and processing techniques can be used, and instant control algorithms can be used to quickly respond to the requirements of real-time changes. At the same time, reasonable control strategies and scheduling algorithms can be designed to ensure the stability and reliability of the system; Step 5, create a visualization interface. In order to facilitate users to adjust parameters and perform decision-making analysis, a visualization interface can be designed to display the optimization results and the feasible solution set. Through the visualization interface, users can more intuitively understand the system performance and optimization effects, improving the usability and ease of use of the system; Step 6, determine the goals of the deep peak shaving transformation based on the operating data and load requirements of the thermal power unit; Step 7, establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraint conditions; Step 8, use the optimization algorithm to solve the model to obtain the optimal deep peak shaving transformation plan.

[0026] In step 7, the objectives considered in the optimization model include improving power generation efficiency, reducing fuel consumption, and controlling emission limits.

[0027] In Step 7, the constraint conditions considered by the optimization model include keeping the power generation within a certain range and meeting the environmental emission standards.

[0028] In Step 2, during the solution process of the genetic algorithm, genetic operations such as crossover, mutation, and selection are considered. During the iterative process of the genetic algorithm, the fitness function is used to evaluate the quality of each individual to select excellent individuals for reproduction.

[0029] In Step 2, during the iterative process of the genetic algorithm, various crossover and mutation methods are adopted to increase the diversity of the population and the search space. During the iterative process of the genetic algorithm, an adaptive parameter adjustment strategy is introduced to improve the convergence and search efficiency of the algorithm.

[0030] In Step 2, during the iterative process of the genetic algorithm, an elitist strategy is adopted to retain excellent individuals to prevent the search from prematurely falling into a local optimal solution.

[0031] In Step 2, during the iterative process of the genetic algorithm, appropriate termination conditions are set, such as reaching the maximum number of iterations or meeting certain convergence criteria.

[0032] In Step 2, during the solution process of the genetic algorithm, parallel computing technology is adopted to improve the solution efficiency and speed.

[0033] In Step 6, the operation data and load demand of the thermal power unit are obtained in real time through sensors.

[0034] A multi-objective optimization planning system for deep peak shaving transformation of thermal power units includes a data acquisition module, a target determination module, an optimization model establishment module, and an optimization solution module. The data acquisition module is used to obtain the operation data and load demand of the thermal power unit. The target determination module is used to determine the goals of the deep peak shaving transformation according to the operation data and load demand. The optimization model establishment module is used to establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraint conditions. The optimization solution module is used to solve the model using an optimization algorithm to obtain the optimal deep peak shaving transformation plan.

[0035] The optimization model establishment module consists of an efficiency unit, an operating cost unit, and an emission limit unit. The efficiency unit converts the input energy or resources into useful outputs while minimizing energy or resource losses as much as possible. The design and optimization of the efficiency unit aim to improve the overall efficiency and performance of the system. The operating cost unit refers to a component in a system, device, or process, whose main function is to calculate and manage the costs during the operation process. The design and optimization of the operating cost unit aim to reduce the operating cost of the system, improve efficiency and economy. The emission limit unit refers to a component in a system, device, or process, whose main function is to monitor and control the emissions of pollutants to meet relevant environmental regulations and standards.

[0036] The optimization and solution module consists of a genetic algorithm unit, an ant colony algorithm unit, a simulated annealing algorithm unit, and a particle swarm optimization algorithm unit. The genetic algorithm unit is an optimization algorithm that simulates the evolution process in nature and searches for the optimal solution to the problem by simulating operations such as gene inheritance, crossover, and mutation. The ant colony algorithm unit is an optimization algorithm that simulates the behavior of ants searching for food and information transfer, and searches for the optimal solution to the problem by simulating the behavior rules and information transfer of ants when solving problems. The simulated annealing algorithm unit is a global optimization algorithm based on random search. By simulating the annealing process in metal smelting, it accepts inferior solutions with a certain probability to jump out of the local optimal solution and search for the global optimal solution. The particle swarm optimization algorithm unit is an optimization algorithm that simulates the group behavior of bird flocks or fish schools and searches for the optimal solution through cooperation and information exchange among individuals.

[0037] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-objective optimization planning method for deep peak shaving transformation of thermal power units, characterized in that, It includes the following steps: Step 1: Conduct data preprocessing. For the uncertainty of system data, data preprocessing techniques can be used to reduce data noise and uncertainty. For example, techniques such as filters and smoothing algorithms can be used to reduce the random fluctuations of data; Step 2: Conduct algorithm optimization. Selecting an appropriate optimization algorithm is the key to optimizing the system. Optimization algorithms such as multi-objective genetic algorithms and multi-objective particle swarm algorithms can be used to solve multi-objective optimization problems. At the same time, methods such as parameter adjustment and heuristic algorithms can be used to improve the efficiency and accuracy of the algorithm; Step 3: Determine the feasible solution set. In multi-objective optimization problems, it is very important to determine the feasible solution set and trade-off factors. Multi-objective decision-making methods can be used to determine the feasible solution set, and the trade-off factors can be adjusted and optimized according to the actual situation; Step 4: Meet the real-time requirements. To meet the real-time requirements, real-time data acquisition and processing techniques can be adopted, and instant control algorithms can be used to quickly respond to the needs of real-time changes. At the same time, reasonable control strategies and scheduling algorithms can be designed to ensure the stability and reliability of the system; Step 5: Create a visualization interface. To facilitate users to adjust parameters and conduct decision-making analysis, a visualization interface can be designed to display the optimization results and the feasible solution set. Through the visualization interface, users can more intuitively understand the system performance and optimization effects, improving the usability and ease of use of the system; Step 6: Determine the goal of deep peak shaving transformation based on the operation data and load demand of the thermal power unit; Step 7: Establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraint conditions; Step 8: Use the optimization algorithm to solve the model to obtain the optimal deep peak shaving transformation plan.

2. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 7, the objectives considered in the optimization model include improving power generation efficiency, reducing fuel consumption, and controlling emission limits.

3. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 7, the constraint conditions considered in the optimization model include keeping the power generation within a certain range and meeting environmental emission standards.

4. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 2, during the solution process of the genetic algorithm, genetic operations such as crossover, mutation, and selection are considered. During the iterative process of the genetic algorithm, the fitness function is used to evaluate the quality of each individual to select excellent individuals for reproduction.

5. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 2, during the iterative process of the genetic algorithm, various crossover and mutation methods are adopted to increase the diversity of the population and the search space. During the iterative process of the genetic algorithm, an adaptive parameter adjustment strategy is introduced to improve the convergence and search efficiency of the algorithm.

6. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 2, during the iterative process of the genetic algorithm, an elite strategy is adopted to retain excellent individuals to prevent the search from prematurely falling into a local optimal solution.

7. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 2, during the iterative process of the genetic algorithm, appropriate termination conditions are set, such as reaching the maximum number of iterations or meeting a certain convergence criterion.

8. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 2, during the solution process of the genetic algorithm, parallel computing technology is adopted to improve the solution efficiency and speed.

9. The multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to claim 1, characterized in that: In Step 6, the operation data and load demand of the thermal power unit are obtained in real time through sensors.

10. A multi-objective optimization planning system for deep peak shaving transformation of thermal power units, applied to the multi-objective optimization planning method for deep peak shaving transformation of thermal power units according to any one of claims 1-9, characterized in that, It includes a data acquisition module, a target determination module, an optimization model establishment module, and an optimization solution module. The data acquisition module is used to obtain the operation data and load demand of the thermal power unit. The target determination module is used to determine the target of the deep peak shaving transformation according to the operation data and load demand. The optimization model establishment module is used to establish a multi-objective optimization model for the deep peak shaving transformation of the thermal power unit based on the objective function and constraints. The optimization solution module is used to solve the model using an optimization algorithm to obtain the optimal deep peak shaving transformation plan.

11. The multi-objective optimization planning system for deep peak shaving transformation of thermal power units according to claim 2, characterized in that: The optimization model establishment module consists of an efficiency unit, an operating cost unit, and an emission limit unit. The efficiency unit converts the input energy or resources into useful outputs while minimizing energy or resource losses as much as possible. The design and optimization of the efficiency unit aim to improve the overall efficiency and performance of the system. The operating cost unit is a component in a system, device, or process, and its main function is to calculate and manage the costs during the operation process. The design and optimization of the operating cost unit aim to reduce the operating cost of the system, improve efficiency and economy. The emission limit unit is a component in a system, device, or process, and its main function is to monitor and control the emissions of pollutants to meet relevant environmental regulations and standards.

12. The multi-objective optimization planning system for deep peak shaving transformation of thermal power units according to claim 2, characterized in that:The optimization solution module consists of a genetic algorithm unit, an ant colony algorithm unit, a simulated annealing algorithm unit, and a particle swarm algorithm unit. The genetic algorithm unit is an optimization algorithm that simulates the evolution process in nature and searches for the optimal solution to the problem by simulating operations such as gene inheritance, crossover, and mutation. The ant colony algorithm unit is an optimization algorithm that simulates the behavior of ants searching for food and information transfer, and searches for the optimal solution to the problem by simulating the behavior rules and information transfer of ants when solving problems. The simulated annealing algorithm unit is a global optimization algorithm based on random search. By simulating the annealing process in metal smelting, it accepts inferior solutions with a certain probability to jump out of the local optimal solution and search for the global optimal solution. The particle swarm algorithm unit is an optimization algorithm that simulates the group behavior of bird flocks or fish schools and searches for the optimal solution through cooperation and information exchange among individuals.

Images