Novel Energy Trading System Based on Deep-Reinforcement Learning in Microgrids

被引：11

作者：

Lee, Seongwoo ^{[1
]}

Seon, Joonho ^{[1
]}

Kyeong, Chanuk ^{[1
]}

Kim, Soohyun ^{[1
]}

Sun, Youngghyu ^{[1
]}

Kim, Jinyoung ^{[1
]}

机构：

[1] Univ Kwangwoon, Dept Elect Convergence Engn, Seoul 01897, South Korea

来源：

ENERGIES | 2021年 / 14卷 / 17期

基金：

新加坡国家研究基金会;

关键词：

microgrid; energy transaction; energy self-sufficient systems; double deep Q-networks (DDQN); double Kelly strategy; TECHNOLOGIES; MANAGEMENT; DEMAND;

D O I：

10.3390/en14175515

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

Inefficiencies in energy trading systems of microgrids are mainly caused by uncertainty in non-stationary operating environments. The problem of uncertainty can be mitigated by analyzing patterns of primary operation parameters and their corresponding actions. In this paper, a novel energy trading system based on a double deep Q-networks (DDQN) algorithm and a double Kelly strategy is proposed for improving profits while reducing dependence on the main grid in the microgrid systems. The DDQN algorithm is proposed in order to select optimized action for improving energy transactions. Additionally, the double Kelly strategy is employed to control the microgrid's energy trading quantity for producing long-term profits. From the simulation results, it is confirmed that the proposed strategies can achieve a significant improvement in the total profits and independence from the main grid via optimized energy transactions.

引用

页数：14

共 35 条

[11]

Harish V. S. K. V., 2019, 2019 2nd International Conference on Power Energy, Environment and Intelligent Control (PEEIC), P259, DOI 10.1109/PEEIC47157.2019.8976848

[12]

Hasselt H. V., 2010, ADV NEURAL INFORM PR

[13] Microgrids: A review of technologies, key drivers, and outstanding issues [J].

Hirsch, Adam ;

Parag, Yael ;

Guerrero, Josep .

RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2018, 90 :402-411

[14] Real-Time Energy Management of a Microgrid Using Deep Reinforcement Learning [J].

Ji, Ying ;

Wang, Jianhui ;

Xu, Jiacan ;

Fang, Xiaoke ;

Zhang, Huaguang .

ENERGIES, 2019, 12 (12)

[15] A NEW INTERPRETATION OF INFORMATION RATE [J].

KELLY, JL .

BELL SYSTEM TECHNICAL JOURNAL, 1956, 35 (04) :917-926

[16] Optimal Energy Scheduling and Transaction Mechanism for Multiple Microgrids [J].

Kim, Boram ;

Bae, Sunghwan ;

Kim, Hongseok .

ENERGIES, 2017, 10 (04)

[17] Energy Management for Microgrids: a Reinforcement Learning Approach [J].

Levent, Tanguy ;

Preux, Philippe ;

Le Pennec, Erwan ;

Badosa, Jordi ;

Henri, Gonzague ;

Bonnassieux, Yvan .

PROCEEDINGS OF 2019 IEEE PES INNOVATIVE SMART GRID TECHNOLOGIES EUROPE (ISGT-EUROPE), 2019,

[18] Seasonal variation in household electricity demand: A comparison of monitored and synthetic daily load profiles [J].

Li, Matthew ;

Allinson, David ;

He, Miaomiao .

ENERGY AND BUILDINGS, 2018, 179 :292-300

[19] Interconnecting Microgrids via the Energy Router with Smart Energy Management [J].

Liu, Yingshu ;

Fang, Yue ;

Li, Jun .

ENERGIES, 2017, 10 (09)

[20] Reinforcement Learning-Based Microgrid Energy Trading With a Reduced Power Plant Schedule [J].

Lu, Xiaozhen ;

Xiao, Xingyu ;

Xiao, Liang ;

Dai, Canhuang ;

Peng, Mugen ;

Poor, H. Vincent .

IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (06) :10728-10737

← 1 2 3 4 →