1.东南大学电气工程学院,江苏省南京市 210096;2.国网江苏省电力有限公司苏州供电分公司,江苏省苏州市 215004
为实现需求侧最大效益,提出一种能够应对复杂环境的基于深度强化学习(DRL)的分层能量调度方法。首先,构建家庭能量管理系统(HEMS)双层框架,通过改变第2层储能系统的充放电功率解决第1层因满足用户用电需求和减少电费所造成负荷集中至低电价时段导致的功率越限,而后根据各用电设备的负荷特性对其进行分类和建模。其次,采用马尔可夫决策过程(MDP)对能量管理问题进行建模,利用奖励函数代替目标函数和约束条件。然后,引入Rainbow算法优化策略以最大化长期收益,实现经济且高效的在线调度。最后,对一个包括光伏板、储能系统、各种用电设备以及电动汽车的家庭进行仿真,验证了所提方法在应对不确定性问题上的有效性和优越性。
国家电网公司科技项目(SGJSSZ00KJJS2000636)。
张甜(1997—),女,硕士,主要研究方向:家庭能量管理、人工智能。E-mail:TianZhangseu@163.com
赵奇(1989—),男,工程师,主要研究方向:配电网故障隔离、电力系统态势感知。E-mail:qzhao1989@163.com
陈中(1975—),男,通信作者,教授,博士生导师,主要研究方向:电力系统稳定与控制、电动汽车与电网互动等。E-mail:zhongchen@seu.edu.cn
1.School of Electrical Engineering, Southeast University, Nanjing 210096, China;2.Suzhou Power Supply Company of State Grid Jiangsu Electric Power Co., Ltd., Suzhou 215004, China
To achieve the maximum benefit on the demand side, a hierarchical energy scheduling method based on deep reinforcement learning (DRL) that can cope with complex environments is proposed. Firstly, a two-tier framework for the home energy management system (HEMS) is established. By changing the charging and discharging power of the second-tier energy storage system, the power over-limit of the first-tier is solved caused by the concentration of the load to the low-electricity-price period for meeting the power demand of users and reducing the electricity bill. Then, electrical appliances are classified and modeled according to their load characteristics. Secondly, Markov decision process (MDP) is used to model the energy management problem. The reward function is employed to replace objective functions and constraints. Moreover, Rainbow algorithm is introduced to optimize the strategy with the goal of maximizing the long-term benefits and achieving online scheduling economically and efficiently. Finally, a simulation is performed on a residential house, which includes solar panels, an energy storage system, multiple electrical appliances, and an electric vehicle, to verify the effectiveness and superiority of the proposed method in dealing with the uncertain problems.
[1] | 张甜,赵奇,陈中,等.基于深度强化学习的家庭能量管理分层优化策略[J].电力系统自动化,2021,45(21):149-158. DOI:10.7500/AEPS20210331010. ZHANG Tian, ZHAO Qi, CHEN Zhong, et al. Hierarchical Optimization Strategy for Home Energy Management Based on Deep Reinforcement Learning[J]. Automation of Electric Power Systems, 2021, 45(21):149-158. DOI:10.7500/AEPS20210331010. |