Evaluating smart grid renewable energy accommodation capability with uncertain generation using deep reinforcement learning

Yongnan Liu, Xin Guan, Jun Li, Di Sun, Tomoaki Ohtsuki, Mohammad Mehedi Hassan, Abdulhameed Alelaiwi

Research output: Contribution to journalArticle

Abstract

Due to environment-friendliness, renewable energy like solar power and wind power is more and more introduced to energy systems all over the world. Simultaneously, high penetrations of wind and solar generation also have brought severe curtailment of wind and solar. How to alleviate curtailment of wind and solar is a crucial problem in evaluating accommodation capability of renewable energy, which reflects the extent of utilization of renewable energy and economic benefits. The uncertainty of renewable energy brings challenges to precisely describe renewable generation, which leads to difficulty in designing effective mechanisms for accommodation capability of renewable energy. Existing work suffers from high computation overhead from frequently updated data, and low precision of describing renewable energy, which leads to less effective policies for renewable energy accommodation and underestimated accommodation capability. To make the most of renewable energy, an algorithm AccCap-DRL based on deep reinforcement learning is proposed. AccCap-DRL partitions a distribution into segments by time intervals, employs WGAN to describe distributions of renewable energy data, and employs DDPG to obtain approximate policies for renewable energy accommodation in different scenarios. Simulation results from real power generation and users’ demand data show high effectiveness of the proposed algorithm, and high efficiency of evaluating accommodation capability.

Original languageEnglish
JournalFuture Generation Computer Systems
DOIs
Publication statusAccepted/In press - 2019 Jan 1

Fingerprint

Reinforcement learning
Solar wind
Solar energy
Wind power
Power generation
Economics

Keywords

  • Accommodation capability
  • Deep reinforcement learning
  • Uncertain renewable energy description

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Evaluating smart grid renewable energy accommodation capability with uncertain generation using deep reinforcement learning. / Liu, Yongnan; Guan, Xin; Li, Jun; Sun, Di; Ohtsuki, Tomoaki; Hassan, Mohammad Mehedi; Alelaiwi, Abdulhameed.

In: Future Generation Computer Systems, 01.01.2019.

Research output: Contribution to journalArticle

@article{0281e0c330e94b4390b48051887e4ad3,
title = "Evaluating smart grid renewable energy accommodation capability with uncertain generation using deep reinforcement learning",
abstract = "Due to environment-friendliness, renewable energy like solar power and wind power is more and more introduced to energy systems all over the world. Simultaneously, high penetrations of wind and solar generation also have brought severe curtailment of wind and solar. How to alleviate curtailment of wind and solar is a crucial problem in evaluating accommodation capability of renewable energy, which reflects the extent of utilization of renewable energy and economic benefits. The uncertainty of renewable energy brings challenges to precisely describe renewable generation, which leads to difficulty in designing effective mechanisms for accommodation capability of renewable energy. Existing work suffers from high computation overhead from frequently updated data, and low precision of describing renewable energy, which leads to less effective policies for renewable energy accommodation and underestimated accommodation capability. To make the most of renewable energy, an algorithm AccCap-DRL based on deep reinforcement learning is proposed. AccCap-DRL partitions a distribution into segments by time intervals, employs WGAN to describe distributions of renewable energy data, and employs DDPG to obtain approximate policies for renewable energy accommodation in different scenarios. Simulation results from real power generation and users’ demand data show high effectiveness of the proposed algorithm, and high efficiency of evaluating accommodation capability.",
keywords = "Accommodation capability, Deep reinforcement learning, Uncertain renewable energy description",
author = "Yongnan Liu and Xin Guan and Jun Li and Di Sun and Tomoaki Ohtsuki and Hassan, {Mohammad Mehedi} and Abdulhameed Alelaiwi",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.future.2019.09.036",
language = "English",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Evaluating smart grid renewable energy accommodation capability with uncertain generation using deep reinforcement learning

AU - Liu, Yongnan

AU - Guan, Xin

AU - Li, Jun

AU - Sun, Di

AU - Ohtsuki, Tomoaki

AU - Hassan, Mohammad Mehedi

AU - Alelaiwi, Abdulhameed

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Due to environment-friendliness, renewable energy like solar power and wind power is more and more introduced to energy systems all over the world. Simultaneously, high penetrations of wind and solar generation also have brought severe curtailment of wind and solar. How to alleviate curtailment of wind and solar is a crucial problem in evaluating accommodation capability of renewable energy, which reflects the extent of utilization of renewable energy and economic benefits. The uncertainty of renewable energy brings challenges to precisely describe renewable generation, which leads to difficulty in designing effective mechanisms for accommodation capability of renewable energy. Existing work suffers from high computation overhead from frequently updated data, and low precision of describing renewable energy, which leads to less effective policies for renewable energy accommodation and underestimated accommodation capability. To make the most of renewable energy, an algorithm AccCap-DRL based on deep reinforcement learning is proposed. AccCap-DRL partitions a distribution into segments by time intervals, employs WGAN to describe distributions of renewable energy data, and employs DDPG to obtain approximate policies for renewable energy accommodation in different scenarios. Simulation results from real power generation and users’ demand data show high effectiveness of the proposed algorithm, and high efficiency of evaluating accommodation capability.

AB - Due to environment-friendliness, renewable energy like solar power and wind power is more and more introduced to energy systems all over the world. Simultaneously, high penetrations of wind and solar generation also have brought severe curtailment of wind and solar. How to alleviate curtailment of wind and solar is a crucial problem in evaluating accommodation capability of renewable energy, which reflects the extent of utilization of renewable energy and economic benefits. The uncertainty of renewable energy brings challenges to precisely describe renewable generation, which leads to difficulty in designing effective mechanisms for accommodation capability of renewable energy. Existing work suffers from high computation overhead from frequently updated data, and low precision of describing renewable energy, which leads to less effective policies for renewable energy accommodation and underestimated accommodation capability. To make the most of renewable energy, an algorithm AccCap-DRL based on deep reinforcement learning is proposed. AccCap-DRL partitions a distribution into segments by time intervals, employs WGAN to describe distributions of renewable energy data, and employs DDPG to obtain approximate policies for renewable energy accommodation in different scenarios. Simulation results from real power generation and users’ demand data show high effectiveness of the proposed algorithm, and high efficiency of evaluating accommodation capability.

KW - Accommodation capability

KW - Deep reinforcement learning

KW - Uncertain renewable energy description

UR - http://www.scopus.com/inward/record.url?scp=85073055557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073055557&partnerID=8YFLogxK

U2 - 10.1016/j.future.2019.09.036

DO - 10.1016/j.future.2019.09.036

M3 - Article

AN - SCOPUS:85073055557

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

ER -