基于深度强化学习的综合能源系统动态经济调度

被引：148

作者：

杨挺

赵黎媛

刘亚闯

冯少康

盆海波

机构：

[1] 智能电网教育部重点实验室(天津大学)

来源：

电力系统自动化 | 2021年 / 45卷 / 05期

基金：

国家重点研发计划; 天津市自然科学基金;

关键词：

综合能源系统; 动态经济调度; 强化学习; 深度确定性策略梯度;

D O I：

暂无

中图分类号：

TM73 [电力系统的调度、管理、通信]; TK01 [能源];

学科分类号：

080707 [能源环境工程]; 120103 [信息系统与信息管理];

摘要：

综合能源系统的优化调度对于实现系统的多能互补和经济运行具有重要意义。然而,系统中可再生能源的间歇性以及用户用能需求的不确定性造成了系统中供需双方的随机波动,传统的调度方法难以准确地适应实际环境的动态变化。针对这一问题,提出了一种考虑可再生能源和负荷时变特性的综合能源系统动态经济调度方法。首先对综合能源系统动态经济调度问题进行数学描述,然后将该调度决策问题表述为强化学习框架,定义了系统的观测状态、调度动作和奖励函数,继而采用深度确定性策略梯度算法进行连续状态和动作空间下的动态调度决策。所提方法不需要对不确定性进行预测或建模,能够动态地对源和荷的随机波动做出响应。最后通过算例仿真验证了所提方法的有效性。

引用

页码：39 / 47

页数：9

共 21 条

[1]

Reinforcement learning in sustainable energy and electric systems: a survey.[J].Ting Yang;Liyuan Zhao;Wei Li;Albert Y. Zomaya.Annual Reviews in Control.2020, prepublish

[2]

An integrated tool for optimal energy scheduling and power quality improvement of a microgrid under multiple demand response schemes.[J].Dimitrios Thomas;Gaspard D’Hoop;Olivier Deblecker;Konstantinos N. Genikomsakis;Christos S. Ioakimidis.Applied Energy.2020, C

[3]

Optimal charging of Electric Vehicles in residential area.[J].Soumia Ayyadi;Hasnae Bilil;Mohamed Maaroufi.Sustainable Energy; Grids and Networks.2019,

[4]

Generic modelling and optimal day-ahead dispatch of micro-energy system considering the price-based integrated demand response.[J].Zexing Chen;Yongjun Zhang;Wenhu Tang;Xiaoming Lin;Qifeng Li.Energy.2019,

[5]

A new quantitative life cycle sustainability assessment framework: Application to integrated energy systems.[J].Salim Moslehi;T. Agami Reddy.Applied Energy.2019,

[6]

Limitations in Energy Management Systems: A Case Study for Resilient Interconnected Microgrids [J].

Gan, Leong Kit ;

Hussain, Akhtar ;

Howey, David A. ;

Kim, Hak-Man .

IEEE TRANSACTIONS ON SMART GRID, 2019, 10 (05) :5675-5685

[7]

Modeling and optimal operation of community integrated energy systems: A case study from China.[J].Chengshan Wang;Chaoxian Lv;Peng Li;Guanyu Song;Shuquan Li;Xiandong Xu;Jianzhong Wu.Applied Energy.2018,

[8]

Fast Decomposed Energy Flow in Large-Scale Integrated Electricity–Gas–Heat Energy Systems.[J].Massrur Hamid Reza;Niknam Taher;Aghaei Jamshid;Shafie khah Miadreza;Catalao Joao P. S..IEEE Transactions on Sustainable Energy.2018, 4

[9]

Reinforcement Learning Approach for Optimal Distributed Energy Management in a Microgrid [J].

Foruzan, Elham ;

Soh, Leen-Kiat ;

Asgarpoor, Sohrab .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2018, 33 (05) :5749-5758

[10]

Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement Learning [J].

Ruelens, Frederik ;

Claessens, Bert J. ;

Vandael, Stijn ;

De Schutter, Bart ;

Babuska, Robert ;

Belmans, Ronnie .

IEEE TRANSACTIONS ON SMART GRID, 2017, 8 (05) :2149-2159

← 1 2 3 →