智能电网中基于增强学习的动态价格优化算法  

Reinforcement Learning-based Optimizing Dynamic Pricing algorithm in smart grid

作　　者：曹俊 孙莹莹 赵航 CAO Jun;SUN Yingying;ZHAO Hang(Zhumadian Power Supply Company,State Grid Henan Electric Power Company,Zhumadian Henan 463000,China)

机构地区：[1]国网河南省电力公司驻马店供电公司,河南驻马店463000

出　　处：《太赫兹科学与电子信息学报》2023年第1期112-118,共7页Journal of Terahertz Science and Electronic Information Technology

摘　　要：动态的电费价格是驱使消费者改变用电消费模式的有效手段,为此,提出基于增强学习的动态价格优化(RLODP)算法。RLODP算法结合电力服务商的利润和消费者的用电成本,对电网负载进行管理;利用增强学习算法,电力服务商自适应地决策零售价格,将动态价格问题转化为离散有限马尔可夫决策过程(MDP),再利用Q-学习算法解决该决策过程。实验结果表明,提出的RLODP算法减少了消费者的用电成本,实现了电网市场中电力供应与需求之间的平衡。Dynamic pricing is one of the most effective ways to encourage customers to change their consumption pattern.Therefore,Reinforcement Learning-based Optimizing Dynamic Pricing(RLODP)algorithm is proposed for energy management in a hierarchical electricity market by considering both service provider’s profit and customers’costs.Using Reinforcement Learning,the SP can adaptively determine the retail electricity price.Dynamic pricing problem is formulated as a discrete finite Markov Decision Process(MDP),and Q-learning is adopted to solve this decision-making problem.Simulation results show that the RLODP algorithm can reduce energy costs for customers,balance the energy supply and the demands in the electricity market.

关 键 词：智能电网 动态需求 电价 增强学习 离散有限马尔可夫决策过程 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]