전력손실 최소화를 위한 심층 강화학습 기반 배전계통 재구성 = Distribution Network Reconfiguration to Minimize Power Loss Using Deep Reinforcement Learning

다국어 초록 (Multilingual Abstract)

Distribution network reconfiguration (DNR) is a technique that changes the status of sectionalizing and tie switches for various purposes such as loss minimization, voltage profile improvement, load leveling, and hosting capacity increase. Although previous algorithms for DNR show good performance, they still have practical limitations. Most of the algorithms assumed that a central coordinator knows all parameters and/or perfect states in a distribution network. Reinforcement learning which is a model-free optimization technique can be a key way to overcome these limitations. This work proposes a DNR scheme using deep reinforcement learning to minimize power loss defined by the amount of line loss and renewable energy curtailment. We model the DNR problem as a Markov decision process (MDP) problem and apply the reinforcement learning algorithm to solve this problem in real-time.
Simulation result using 33-bus radial distribution system shows that the proposed scheme shows similar performance compared to an existing method which uses all information on the distribution network

참고문헌 (Reference)

1 김영환, "재생에너지의 전력계통 수용 증대를 위한 ESS 운영방안" 대한전기학회 67 (67): 1401-1407, 2018

2 명호산, "재생에너지 출력제한에 따른 출력량 배분 방안 연구" 한국전기전자학회 23 (23): 173-180, 2019

3 Ministry of Trade, Industry and Energy, the Republic of Korea, "재생에너지 3020 이행계획(안) 발표"

4 Q. Yang, "Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning" 11 (11): 2313-2323, 2020

5 M. Bellemare, "The arcade learning environment : An evaluation platform for general agents" 47 : 253-279, 2013

6 J. Kober, "Reinforcement learning in robotics : a survey" 32 (32): 1238-1278, 2013

7 S. Kim, "Reinforcement learning based energy management algorithm for smart energy buildings" 11 (11): 2010-, 2018

8 T. Markvart, "Practical handbook of photovoltaics : fundamentals and applications" Elsevier 49-51, 2003

9 V. Mnih, "Playing atari with deep reinforcement learning"

10 M. Mosbah, "Optimum dynamic distribution network reconfiguration using minimum spanning tree algorithm" 1-6, 2017

11 J. Z. Zhu, "Optimal reconfiguration of electrical distribution network using the refined genetic algorithm" 62 (62): 37-42, 2002

12 D. Silver, "Mastering the Game of Go without Human Knowledge" 550 : 354-359, 2017

13 S. S. Gu, "Interpolated policy gradient : Merging on-policy and off-policy gradient estimation for deep reinforcement learning" 3846-3855, 2017

14 S. Kim, "Increasing Hosting Capacity of Distribution Feeders by Analysis of Generation and Consumption" 5 (5): 295-309, 2019

15 J. Seuss, "Improving distribution network PV hosting capacity via smart inverter reactive power support" 1-5, 2015

16 B. Novoselnik, "Dynamic reconfiguration of electrical power distribution systems with distributed generation and storage" 48 (48): 136-141, 2015

17 F. V. Dantas, "Dynamic reconfiguration of distribution network systems:A key flexibility option for res integration" 1-6, 2017

18 Y. Gao, "Dynamic Distribution Network Reconfiguration Using Reinforcement Learning" 1-7, 2019

19 A. G. Patel, "Distribution network reconfiguration for loss reduction" IEEE 3937-3941, 2016

20 T. Li, "Deep Reinforcement Learning Based Residential Demand Side Management With Edge Computing" IEEE 1-6, 2019

21 F. Capitanescu, "Assessing the potential of network reconfiguration to improve distributed generation hosting capacity in active distribution systems" 30 (30): 346-356, 2014

22 E. A. Feinberg, "A rolling horizon approach to distribution feeder reconfiguration with switching costs" IEEE 339-344, 2011

23 M. M. Haque, "A review of high PV penetrations in LV distribution networks : Present status, impacts and mitigation measures" 62 : 1195-1208, 2016

24 A. M. Imran, "A new power system reconfiguration scheme for power loss minimization and voltage profile enhancement using fireworks algorithm" 62 : 312-322, 2014

25 Iowa State University, "A Real 240-Node Distribution System with One-Year Smart Meter Data"

26 Ministry of Trade, Industry and Energy, the Republic of Korea, "1 MW 이하 소규모 신재생발전 전력망 접속보장"