2012
DOI: 10.12720/sgce.1.1.122-128
|View full text |Cite
|
Sign up to set email alerts
|

Smart Scheduling Strategy for Islanded Microgrid Based on Reinforcement Learning Algorithm

Abstract: This paper investigates a hierarchical Automatic Generation Control (AGC) strategy for an islanded microgrid, including wind power, solar photovoltaic, micro turbines, small hydropower and energy storage devices. The upper AGC is for central scheduling. The bottom AGC is to optimize the allocation factors, expecting to meet the requirement of energy-saving generation dispatching (ESGD). Three different bottom controllers are presented. Two of them are designed based on reinforcement learning (RL) algorithm. In… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2015
2015
2022
2022

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 7 publications
0
4
0
Order By: Relevance
“…[73] proposes a partially observable MDP model to address the stochastic nature of future electricity loads and renewable power generation. A reinforcement learning algorithm for hierarchical automatic generation control is proposed in [74] to achieve multi-objective dynamic optimal allocation of a microgrid in island mode. Distributed multi-energy systems optimization problem is addressed in [75] using an alternative approach based on multi-agent reinforcement learning.…”
Section: Addressing Uncertainty Issues In Smart Gridsmentioning
confidence: 99%
“…[73] proposes a partially observable MDP model to address the stochastic nature of future electricity loads and renewable power generation. A reinforcement learning algorithm for hierarchical automatic generation control is proposed in [74] to achieve multi-objective dynamic optimal allocation of a microgrid in island mode. Distributed multi-energy systems optimization problem is addressed in [75] using an alternative approach based on multi-agent reinforcement learning.…”
Section: Addressing Uncertainty Issues In Smart Gridsmentioning
confidence: 99%
“…The concept of a virtual synchronous generator in microgrid was proposed in [6], and the feasibility of applying centralized frequency control of a traditional power system into microgrid was analyzed in detail. In [7], a centralized automatic generation control (AGC) controller based on reinforcement learning in an island operation mode was proposed, which realized the AGC and frequency regulation in microgrid. However, considering utilization of distributed energy, it is difficult to realize cooperative control between provincial dispatching and regional dispatching in AGC-centralized control mode [8].…”
Section: Introductionmentioning
confidence: 99%
“…The DR for frequency regulation in MGs was considered in , but the UC and optimization of operation planning were neglected. The authors in proposed smart scheduling and automatic secondary regulation only for islanded operation without committing units or using additional resources, like LS or DR. Reference presented an analysis and systemization of Automatic Generation Control (AGC) in MGs without analysis of UC, storage commitment or DR. An advanced control architecture by operating a self‐organizing multi‐agent system for MGs was presented in , but only for grid‐connected operation. A comprehensive double‐layer solution for MGMS in grid‐connected and island modes was presented in , but the authors did not address real‐time dispatching and emergency island operation.…”
Section: Introductionmentioning
confidence: 99%
“…The main advantages of the proposed solution (compared with previously published approaches ) are as follows: Increased reliability (reduction in outage time) for critical loads. Improvement in energy efficiency (economy). Reduction of carbon emissions. Management of ‘bumpless’ transition from grid‐connected to island mode (during planned and emergency islanding). Maintaining the voltages inside the pre‐defined technical limits. Keeping the power flow through MG's Point of Common Coupling (PCC) and system's frequency within the desired technical limits. Providing the detailed information about the MG condition to the system's operator. …”
Section: Introductionmentioning
confidence: 99%