Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning

Saeed  Hasanvand; Mehdi Rafiei Foroushani; Meysam Gheisarnejad; Mohammad Hassan Khooban

doi:10.1109/TTE.2020.2983247

Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning

Saeed Hasanvand , Mehdi Rafiei Foroushani, Meysam Gheisarnejad, Mohammad Hassan Khooban

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

81 Citations (Scopus)

Abstract

Environmental pollutants, as a global concern, have led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in all-electric ships, as well as power grids, has increased in recent years. In this article, in order to have a zero-emission and cost-effective energy management in an all-electric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, the loss of load expectation (LOLE) as a reliability index is considered in the energy management context and the problem is solved by the deep reinforcement learning in a multiobjective manner. The results of the consideration of two common standards, including DNVGL-ST-0033 and DNVGL-ST-0373, demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.

Original language	English
Article number	9046850
Journal	IEEE Transactions on Transportation Electrification
Volume	6
Issue	2
Pages (from-to)	832-843
Number of pages	12
ISSN	2332-7782
DOIs	https://doi.org/10.1109/TTE.2020.2983247
Publication status	Published - Jun 2020

Keywords

Deep Reinforcement Learning
Energy Management
Fuel Cell
Hardware-in-the-Loop (HIL)
Loss of Load Expectation (LOLE)
Zero-emission ships
SYSTEM
Boats
STRATEGY
ALGORITHM
RELIABILITY
Batteries
MICROGRIDS
Fuel cells
Deep reinforcement learning (RL)
energy management
PROPULSION
loss of load expectation (LOLE)
hardware-in-the-loop (HIL)
fuel cell
OPERATION
OPTIMIZATION
zero-emission ships
Power system reliability
Reliability
ENERGY-MANAGEMENT
Energy management

Access to Document

10.1109/TTE.2020.2983247

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9046850

Library access?

Check availability with the Royal Danish Library

Cite this

@article{accf489fce004d7abf4556aa6c690919,

title = "Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning",

abstract = "Environmental pollutants, as a global concern, have led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in all-electric ships, as well as power grids, has increased in recent years. In this article, in order to have a zero-emission and cost-effective energy management in an all-electric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, the loss of load expectation (LOLE) as a reliability index is considered in the energy management context and the problem is solved by the deep reinforcement learning in a multiobjective manner. The results of the consideration of two common standards, including DNVGL-ST-0033 and DNVGL-ST-0373, demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.",

keywords = "Deep Reinforcement Learning, Energy Management, Fuel Cell, Hardware-in-the-Loop (HIL), Loss of Load Expectation (LOLE), Zero-emission ships, SYSTEM, Boats, STRATEGY, ALGORITHM, RELIABILITY, Batteries, MICROGRIDS, Fuel cells, Deep reinforcement learning (RL), energy management, PROPULSION, loss of load expectation (LOLE), hardware-in-the-loop (HIL), fuel cell, OPERATION, OPTIMIZATION, zero-emission ships, Power system reliability, Reliability, ENERGY-MANAGEMENT, Energy management",

author = "Saeed Hasanvand and {Rafiei Foroushani}, Mehdi and Meysam Gheisarnejad and Khooban, {Mohammad Hassan}",

year = "2020",

month = jun,

doi = "10.1109/TTE.2020.2983247",

language = "English",

volume = "6",

pages = "832--843",

journal = "IEEE Transactions on Transportation Electrification",

issn = "2332-7782",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning. / Hasanvand , Saeed ; Rafiei Foroushani, Mehdi; Gheisarnejad, Meysam et al.
In: IEEE Transactions on Transportation Electrification, Vol. 6, No. 2, 9046850, 06.2020, p. 832-843.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - Reliable Power Scheduling of an Emission-Free Ship

T2 - Multi-Objective Deep Reinforcement Learning

AU - Hasanvand , Saeed

AU - Rafiei Foroushani, Mehdi

AU - Gheisarnejad, Meysam

AU - Khooban, Mohammad Hassan

PY - 2020/6

Y1 - 2020/6

N2 - Environmental pollutants, as a global concern, have led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in all-electric ships, as well as power grids, has increased in recent years. In this article, in order to have a zero-emission and cost-effective energy management in an all-electric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, the loss of load expectation (LOLE) as a reliability index is considered in the energy management context and the problem is solved by the deep reinforcement learning in a multiobjective manner. The results of the consideration of two common standards, including DNVGL-ST-0033 and DNVGL-ST-0373, demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.

AB - Environmental pollutants, as a global concern, have led to a general increase in the utilization of renewable energy resources instead of fossil fuels. Accordingly, the penetration of these resources in all-electric ships, as well as power grids, has increased in recent years. In this article, in order to have a zero-emission and cost-effective energy management in an all-electric ferry boat, a new reliable and optimal power scheduling is presented that uses fuel cell and battery energy storage systems. Furthermore, the real information including load profile and paths is considered for the case study to assess the feasibility and superiority of the proposed approach. In addition to the cost of energy management, to have a reliable combination of the proposed resources, the loss of load expectation (LOLE) as a reliability index is considered in the energy management context and the problem is solved by the deep reinforcement learning in a multiobjective manner. The results of the consideration of two common standards, including DNVGL-ST-0033 and DNVGL-ST-0373, demonstrate that the proposed energy management method is applicable in industrial applications. Finally, the real-time simulation-based hardware-in-the-loop (HIL) is conducted to validate the performance and efficacy of the suggested power scheduling for the emission-free ships.

KW - Deep Reinforcement Learning

KW - Energy Management

KW - Fuel Cell

KW - Hardware-in-the-Loop (HIL)

KW - Loss of Load Expectation (LOLE)

KW - Zero-emission ships

KW - SYSTEM

KW - Boats

KW - STRATEGY

KW - ALGORITHM

KW - RELIABILITY

KW - Batteries

KW - MICROGRIDS

KW - Fuel cells

KW - Deep reinforcement learning (RL)

KW - energy management

KW - PROPULSION

KW - loss of load expectation (LOLE)

KW - hardware-in-the-loop (HIL)

KW - fuel cell

KW - OPERATION

KW - OPTIMIZATION

KW - zero-emission ships

KW - Power system reliability

KW - Reliability

KW - ENERGY-MANAGEMENT

KW - Energy management

U2 - 10.1109/TTE.2020.2983247

DO - 10.1109/TTE.2020.2983247

M3 - Journal article

SN - 2332-7782

VL - 6

SP - 832

EP - 843

JO - IEEE Transactions on Transportation Electrification

JF - IEEE Transactions on Transportation Electrification

IS - 2

M1 - 9046850

ER -

Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning

Abstract

Keywords

Access to Document

Library access?

Fingerprint

Cite this