欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
通过研究各种分布式电源的发电特性，搭建了含风电、光伏发电、飞轮储能、小水电、微型燃气轮机与负荷的微电网负荷频率控制（LoadFrequencyControl，LFC）模型，其中小水电和微型燃气轮机为调频机组。将大型互联电网中的集中式自动发电控制（AutomaticGenerationControl，AGC）原理引入微电网，并结合基于平均报酬模型的多步R（λ）学习算法，提出了一种孤岛运行模式下基于强化学习的AGC控制器，以实现对微网的智能发电控制与频率调整。仿真试验分析表明，与PI控制、Q学习和Q（λ）学习相比，所提出的R（λ）控制器具有快速收敛特性和良好的动态性能以及较强的模型适应性。
英文摘要：
This paper studies the characte.ristics of a variety of distributed generations, and establishes a microgrid load frequency control （LFC） model containing a wind turbine, photovoltaic generation, flywheel energy storage, small.hydro unit, a micro gas turbine and the load. In the microgird LFC model, the hydro unit and the micro gas turbine are adopted as AGC units. The automatic generation control （AGC） principle for the large interconnected power systems is introduced into the microgrid, and the multi-step R （λ） learning is applied to propose a novel reinforcement learning based AGC controller so as to achieve the smart generation control and frequency adjustment for microgrids islanded operation. Simulation analysis and comparison with PI control, Q-learning and Q （λ） learning show that the R （λ） learning controller has rapid convergence rate and good dynamic performance as well as strong model adaptability.
同期刊论文项目
同项目期刊论文
Stochastic Optimal CPS Relaxed Control Methodology for Interconnected Power Systems Using Q-Learning
Stochastic optimal generation command dispatch based on improved hierarchical reinforcement learning
Stochastic Optimal Relaxed Automatic Generation Control in Non-Markov Environment Based on Multi-Ste
Equilibrium-Inspired Multiple Group Search Optimizer with Synergistic Learning for Multi-objective E
A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algo
Approxiamate ideal multi-objective solution Q(λ) learning for optimal carbon-energy combined-flow in
Equilibrium-Inspired Multiple Group Search Optimizer with Synergistic Learning for Multiobjective El
期刊信息
位置：