Electric Vehicle Integration for Grid Services Using AI, Optimization, and Blockchain
Electric Vehicle Integration for Grid Services Using AI, Optimization, and Blockchain
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153125
- ISBN
- 9798346852278
- DDC
- 621
- 서명/저자
- Electric Vehicle Integration for Grid Services Using AI, Optimization, and Blockchain
- 발행사항
- [Sl] : University of California, Los Angeles, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 135 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Gadh, Rajit.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- 초록/해제
- 요약The rapid adoption of electric vehicles (EVs) presents both challenges and opportunities for modern power grids. This dissertation advances EV integration within power grid systems through four interconnected contributions. First, the application of transfer learning and model-agnostic meta-learning techniques enhance short-term EV charging load forecasting in an evolving EV landscape, reducing forecasting errors by up to 61% compared to traditional machine learning approaches. These improvements enable grid operators to better manage dynamic charging patterns across diverse geographical conditions with limited historical data.Second, an optimization framework leveraging Vehicle-to-Grid (V2G) technology demonstrates potential for grid congestion relief through strategic charging and discharging based on congestion component of Locational Marginal Prices. While EVs can contribute to grid stability, economic analysis reveals that participation typically results in net monetary losses under current market models when accounting for seasonal variations and battery degradation costs.Third, a blockchain-based framework addresses battery degradation concerns in V2G applications through real-time tracking and assessment. The framework dynamically updates degradation cost parameters based on charging activities and environmental conditions, enabling transparent management of battery lifecycle costs and informed V2G participation.Fourth, an optimal sizing method for Battery Energy Storage Systems (BESS) integration with electric bus charging infrastructure in urban transit networks optimizes is discussed for both depot and en-route charging scenarios. The resulting framework demonstrates how strategic storage deployment manages peak loads and reduces operational costs, enhancing the economic viability of electric public transit.These contributions advance the development of efficient and resilient electrified transportation systems through innovative solutions in load forecasting, grid services, battery management, and infrastructure cost reduction, supporting the global transition to sustainable energy.
- 일반주제명
- Energy
- 일반주제명
- Electrical engineering
- 기타저자
- University of California, Los Angeles Mechanical Engineering 0330
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017165113
■00520250211153125
■006m o d
■007cr#unu||||||||
■020 ▼a9798346852278
■035 ▼a(MiAaPQ)AAI31764718
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a621
■1001 ▼aNarayana Gowda, Shashank.
■24510▼aElectric Vehicle Integration for Grid Services Using AI, Optimization, and Blockchain
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a135 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Gadh, Rajit.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aThe rapid adoption of electric vehicles (EVs) presents both challenges and opportunities for modern power grids. This dissertation advances EV integration within power grid systems through four interconnected contributions. First, the application of transfer learning and model-agnostic meta-learning techniques enhance short-term EV charging load forecasting in an evolving EV landscape, reducing forecasting errors by up to 61% compared to traditional machine learning approaches. These improvements enable grid operators to better manage dynamic charging patterns across diverse geographical conditions with limited historical data.Second, an optimization framework leveraging Vehicle-to-Grid (V2G) technology demonstrates potential for grid congestion relief through strategic charging and discharging based on congestion component of Locational Marginal Prices. While EVs can contribute to grid stability, economic analysis reveals that participation typically results in net monetary losses under current market models when accounting for seasonal variations and battery degradation costs.Third, a blockchain-based framework addresses battery degradation concerns in V2G applications through real-time tracking and assessment. The framework dynamically updates degradation cost parameters based on charging activities and environmental conditions, enabling transparent management of battery lifecycle costs and informed V2G participation.Fourth, an optimal sizing method for Battery Energy Storage Systems (BESS) integration with electric bus charging infrastructure in urban transit networks optimizes is discussed for both depot and en-route charging scenarios. The resulting framework demonstrates how strategic storage deployment manages peak loads and reduces operational costs, enhancing the economic viability of electric public transit.These contributions advance the development of efficient and resilient electrified transportation systems through innovative solutions in load forecasting, grid services, battery management, and infrastructure cost reduction, supporting the global transition to sustainable energy.
■590 ▼aSchool code: 0031.
■650 4▼aEnergy
■650 4▼aElectrical engineering
■653 ▼aElectric vehicles
■653 ▼aMeta-learning techniques
■653 ▼aBattery degradation
■653 ▼aBattery Energy Storage Systems
■653 ▼aBattery management
■690 ▼a0791
■690 ▼a0800
■690 ▼a0544
■71020▼aUniversity of California, Los Angeles▼bMechanical Engineering 0330.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17165113▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


