火力发电站
调度(生产过程)
计算机科学
减速器
热的
数学优化
工程类
汽车工程
控制理论(社会学)
机械工程
人工智能
废物管理
数学
物理
气象学
控制(管理)
出处
期刊:Journal of physics
[IOP Publishing]
日期:2023-02-01
卷期号:2442 (1): 012009-012009
标识
DOI:10.1088/1742-6596/2442/1/012009
摘要
Abstract Optimal dispatch is one of the key technologies to realize the efficient and economical operation of the thermal power system in thermal power plants. In order to reduce the energy consumption of thermal power system in thermal power plants, ensure the optimal dispatching effect and improve the efficiency of optimal dispatching, this paper introduces deep reinforcement learning to design a new optimal dispatching method for thermal power system in thermal power plants. The thermal power system structure of thermal power plant is analyzed, and the models of boiler, steam turbine and temperature and pressure reducer are established. The optimal scheduling problem of steam turbine and boiler thermal system is studied. By setting the objective function and determining the constraint function, the relevant optimal scheduling model is constructed. The SAC algorithm in deep reinforcement learning is used to solve the model to achieve the important goal of optimal scheduling. The experimental results show that the total fuel consumption of the proposed method is small, and the proposed method has a better optimal scheduling effect of thermal power system in thermal power plants, and can effectively improve the optimal scheduling efficiency.
科研通智能强力驱动
Strongly Powered by AbleSci AI