Towards Optimal Unit Commitment of Future Ship Energy Systems

Janne Huotari

Towards Optimal Unit Commitment of Future Ship Energy Systems

Julkaisun otsikon käännös: Kohti Tulevien Laivojen Energiajärjestelmien Optimaalista Ohjausta

Janne Huotari

Tutkimustuotos: Doctoral Thesis › Collection of Articles

Abstrakti

Merenkulkusektori tulee kokemaan ennennäkemättömän energiamurroksen tulevina vuosikymmeninä. Kansainvälinen merenkulkujärjestö on asettanut tavoitteen, jonka mukaan laivoista syntyvien kasvihuonepäästöjen tulee vähentyä 50 % verrattuna vuoden 2008 päästötasoon. Tämän tavoitteen saavuttaminen edellyttää merkittäviä edistysaskeleita laivojen operatiivisessa toiminnassa, uusien teknologioiden käytössä sekä vanhojen teknologioiden astettaisessa parantamisessa. Tässä väitöskirjassa tutkitaan ja kehitetään viimeisintä tutkimusta edustavia menetelmiä laivan energiajärjestelmän ohjaukseen, sekä laivan nopeuden optimointiin. Laivan energiajärjestelmän tehokas ohjaus on ensiarvoisen tärkeää operatiivisten kustannusten ja kasvihuonepäästöjen minimoimiseksi, mutta haastavaa koska järjestelmässä on yleensä useita eri teholähteitä. Tämä johtaa väitöskirjan tärkeimpään tutkimuskysymykseen: "Kuinka ohjata laivan energiajärjestelmää optimaalisesti reaaliajassa?". Energiajärjestelmän ohjaukseen esitetään koneoppimiseen ja optimointiin perustuvia menetelmiä. Molemmat menetelmät pohjautuvat mitattuun dataan todellisten laivojen operointiprofiileista. Ohjauksen koneoppimismallissa käytettiin vahvistusoppimis -menetelmiä luomaan automaattisesti ohjaukseen oppiva järjestelmä. Tällaisen metodin vahvuus on oppimisen dynaamisuus, eli ohjain voi kehittyä muuttuvien järjestelmien tahdissa. Lisäksi koulutusvaiheessa ohjain voi löytää yllättäviäkin ratkaisuja joita muut menetelmät eivät löytäisi. Optimointiin perustuva ohjausmetodi koostui kahdesta osasta: tehokysynnän ennustamisesta Gaussin prosessilla ja ennustuksen perusteella energiajärjestelmän käytön optimoinnista sekoitettujen kokonaislukujen lineaarisella optimoinnilla. Tehokysynnän ennustamiseen käytettiin laivan nopeusprofiilia, jonka oletettiin olevan tiedossa etukäteen. Menetelmä osoittautui tehokkaaksi ja monipuoliseksi ohjausmetodiksi. Lisäksi Gaussin prosessin käyttö tuotti probabilistisen tehokysynnän ennusteen, joka mahdollistaa modernien stokastisten ja robustien optimointimenetelmien käytön ohjauksessa. Tehokkaat energiajärjestelmän ohjausmetodit perustuvat pitkälti ennustettuun tehokysyntään, kuten tässäkin työssä optimointiin perustuvassa metodissa. Tehokysynnän tärkein yksittäinen selittäjä on laivan nopeus, joten tehokysynnän ennuste on vahvasti riippuvainen laivan tulevan nopeusprofiilin arviosta. Tästä syystä väitöskirjassa tutkittiin myös optimaalisen nopeusprofiilin määrittämistä etukäteen tietylle reitille ja aikataululle. Nopeusprofiilin optimointiin esitettiin laskentatehokasta konveksia optimointimallia, joka tuotti tuloksena jatkuvan laivan nopeusprofiilin.

Julkaisun otsikon käännös	Kohti Tulevien Laivojen Energiajärjestelmien Optimaalista Ohjausta
Alkuperäiskieli	Englanti
Pätevyys	Tohtorintutkinto
Myöntävä instituutio	Aalto-yliopisto
Valvoja/neuvonantaja	Tammi, Kari, Vastuuprofessori
Kustantaja	Aalto University
Painoksen ISBN	978-952-64-0616-9
Sähköinen ISBN	978-952-64-0617-6
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	G5 Artikkeliväitöskirja

Tutkimusalat

laiva
energiajärjestelmä
sekoitettujen kokonaislukujen ohjelmointi
konveksi optimointi
vahvistusoppiminen
tehokysynnän ennustus
nopeusoptimointi

YK:n kestävän kehityksen tavoitteet

Tämä tuotos edistää seuraavia kestävän kehityksen tavoitteita:

Pääsy asiakirjaan

http://urn.fi/URN:ISBN:978-952-64-0617-6

Siteeraa tätä

@phdthesis{e7cdc154b89843aa886a7ae33733ee97,

title = "Towards Optimal Unit Commitment of Future Ship Energy Systems",

abstract = "The maritime sector is currently undergoing a monumental energy transition. The international maritime organization has set a goal for reducing ship-borne antrophogenic greenhouse gas emissions by 50 % by 2050 compared to the emission levels in 2008. To reach this goal, significant advancements must be made in the way the existing tonnage is operated, new energy efficient technologies must be adopted and old technologies need to be enhanced. In this dissertation, state-of-the-art methodologies for ship energy system unit commitment and speed profile optimization are studied and developed. Efficient unit commitment of a ship's energy system is crucially important to minimize operational costs and greenhouse gas emissions. However, developing an effective commitment logic is difficult due to the complex nature of such systems. This leads to the primary research problem of this dissertation: {"}How to achieve real-time and optimal unit commitment control a ship's energy system of arbitrary complexity?{"}. Novel methods based on machine learning and mathematical optimization are proposed for this task. Both of these methods are developed and their performance tested based on real operational ship data. The method based on machine learning leveraged reinforcement learning to produce a unit commitment method that learned to control the energy system by itself. The benefit of such an approach is the dynamic nature of learning, where the controller can automatically evolve in accordance to a changing environment. In addition, the trial-and-error based learning phase can reveal surprisingly effective control sequences unattainable by other methods. The method based on mathematical optimization consisted of two parts: prediction of future power demand via a Gaussian process, and a mixed-integer linear program for optimizing the unit commitment response of the energy system based on the demand prediction. The power demand was predicted according to the expected future speed profile of the ship, which was assumed to be known beforehand. The method proved out to be an effective and holistic approach for real-time ship energy system unit commitment. Effective ship energy system unit commitment methodologies are based on a prediction of future power demand, as was the case in the mathematical optimization based method in this work. As the primary predictor of power demand is the speed of a ship, the quality of a power demand prediction is highly dependent on the accuracy of future speed profile estimation. Because of this, this dissertation also focused on research revolving around the optimization of a ship's speed profile for a predetermined route and schedule. A computationally efficient convex optimization model was proposed for ship speed profile optimization, which produced a continuous speed profile proposition as a result.",

keywords = "ship, energy system, unit commitment, mixed-integer linear programming, convex optimization, reinforcement learning, power demand prediction, speed optimization, laiva, energiaj{\"a}rjestelm{\"a}, sekoitettujen kokonaislukujen ohjelmointi, konveksi optimointi, vahvistusoppiminen, tehokysynn{\"a}n ennustus, nopeusoptimointi, ship, energy system, unit commitment, mixed-integer linear programming, convex optimization, reinforcement learning, power demand prediction, speed optimization",

author = "Janne Huotari",

year = "2021",

language = "English",

isbn = "978-952-64-0616-9",

series = "Aalto University publication series DOCTORAL DISSERTATIONS",

publisher = "Aalto University",

number = "170",

address = "Finland",

school = "Aalto University",

}

TY - BOOK

T1 - Towards Optimal Unit Commitment of Future Ship Energy Systems

AU - Huotari, Janne

PY - 2021

Y1 - 2021

N2 - The maritime sector is currently undergoing a monumental energy transition. The international maritime organization has set a goal for reducing ship-borne antrophogenic greenhouse gas emissions by 50 % by 2050 compared to the emission levels in 2008. To reach this goal, significant advancements must be made in the way the existing tonnage is operated, new energy efficient technologies must be adopted and old technologies need to be enhanced. In this dissertation, state-of-the-art methodologies for ship energy system unit commitment and speed profile optimization are studied and developed. Efficient unit commitment of a ship's energy system is crucially important to minimize operational costs and greenhouse gas emissions. However, developing an effective commitment logic is difficult due to the complex nature of such systems. This leads to the primary research problem of this dissertation: "How to achieve real-time and optimal unit commitment control a ship's energy system of arbitrary complexity?". Novel methods based on machine learning and mathematical optimization are proposed for this task. Both of these methods are developed and their performance tested based on real operational ship data. The method based on machine learning leveraged reinforcement learning to produce a unit commitment method that learned to control the energy system by itself. The benefit of such an approach is the dynamic nature of learning, where the controller can automatically evolve in accordance to a changing environment. In addition, the trial-and-error based learning phase can reveal surprisingly effective control sequences unattainable by other methods. The method based on mathematical optimization consisted of two parts: prediction of future power demand via a Gaussian process, and a mixed-integer linear program for optimizing the unit commitment response of the energy system based on the demand prediction. The power demand was predicted according to the expected future speed profile of the ship, which was assumed to be known beforehand. The method proved out to be an effective and holistic approach for real-time ship energy system unit commitment. Effective ship energy system unit commitment methodologies are based on a prediction of future power demand, as was the case in the mathematical optimization based method in this work. As the primary predictor of power demand is the speed of a ship, the quality of a power demand prediction is highly dependent on the accuracy of future speed profile estimation. Because of this, this dissertation also focused on research revolving around the optimization of a ship's speed profile for a predetermined route and schedule. A computationally efficient convex optimization model was proposed for ship speed profile optimization, which produced a continuous speed profile proposition as a result.

AB - The maritime sector is currently undergoing a monumental energy transition. The international maritime organization has set a goal for reducing ship-borne antrophogenic greenhouse gas emissions by 50 % by 2050 compared to the emission levels in 2008. To reach this goal, significant advancements must be made in the way the existing tonnage is operated, new energy efficient technologies must be adopted and old technologies need to be enhanced. In this dissertation, state-of-the-art methodologies for ship energy system unit commitment and speed profile optimization are studied and developed. Efficient unit commitment of a ship's energy system is crucially important to minimize operational costs and greenhouse gas emissions. However, developing an effective commitment logic is difficult due to the complex nature of such systems. This leads to the primary research problem of this dissertation: "How to achieve real-time and optimal unit commitment control a ship's energy system of arbitrary complexity?". Novel methods based on machine learning and mathematical optimization are proposed for this task. Both of these methods are developed and their performance tested based on real operational ship data. The method based on machine learning leveraged reinforcement learning to produce a unit commitment method that learned to control the energy system by itself. The benefit of such an approach is the dynamic nature of learning, where the controller can automatically evolve in accordance to a changing environment. In addition, the trial-and-error based learning phase can reveal surprisingly effective control sequences unattainable by other methods. The method based on mathematical optimization consisted of two parts: prediction of future power demand via a Gaussian process, and a mixed-integer linear program for optimizing the unit commitment response of the energy system based on the demand prediction. The power demand was predicted according to the expected future speed profile of the ship, which was assumed to be known beforehand. The method proved out to be an effective and holistic approach for real-time ship energy system unit commitment. Effective ship energy system unit commitment methodologies are based on a prediction of future power demand, as was the case in the mathematical optimization based method in this work. As the primary predictor of power demand is the speed of a ship, the quality of a power demand prediction is highly dependent on the accuracy of future speed profile estimation. Because of this, this dissertation also focused on research revolving around the optimization of a ship's speed profile for a predetermined route and schedule. A computationally efficient convex optimization model was proposed for ship speed profile optimization, which produced a continuous speed profile proposition as a result.

KW - ship

KW - energy system

KW - unit commitment

KW - mixed-integer linear programming

KW - convex optimization

KW - reinforcement learning

KW - power demand prediction

KW - speed optimization

KW - laiva

KW - energiajärjestelmä

KW - sekoitettujen kokonaislukujen ohjelmointi

KW - konveksi optimointi

KW - vahvistusoppiminen

KW - tehokysynnän ennustus

KW - nopeusoptimointi

KW - ship

KW - energy system

KW - unit commitment

KW - mixed-integer linear programming

KW - convex optimization

KW - reinforcement learning

KW - power demand prediction

KW - speed optimization

M3 - Doctoral Thesis

SN - 978-952-64-0616-9

T3 - Aalto University publication series DOCTORAL DISSERTATIONS

PB - Aalto University

ER -

Towards Optimal Unit Commitment of Future Ship Energy Systems

Abstrakti

Tutkimusalat

YK:n kestävän kehityksen tavoitteet

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä