4.8 Article

Long-term microgrid expansion planning with resilience and environmental benefits using deep reinforcement learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review Green & Sustainable Science & Technology

A review of reinforcement learning based energy management systems for electrified powertrains: Progress, challenge, and potential solution

Akhil Hannegudda Ganesh et al.

Summary: This article discusses the impact of internal combustion engine-powered automobiles on climate change and the progress of electrified powertrains, focusing on the application of Reinforcement Learning (RL) based algorithms in the field. It reviews the recent research and potential solutions for challenges in the area of RL-based EMS.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Review Engineering, Electrical & Electronic

Enhancing distribution system resilience against extreme weather events: Concept review, algorithm summary, and future vision

Qingxin Shi et al.

Summary: This paper focuses on the resilience of distribution systems and its enhancement strategies. By reviewing previous studies, the paper presents the resources and mathematical models for enhancing resilience, and compares the objectives, models, variables, and solution algorithms of each study. Finally, the paper proposes the roadmap for resilient distribution systems and suggests future research directions.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Article Green & Sustainable Science & Technology

Reliability aspects in microgrid design and planning: Status and power electronics-induced challenges

Monika Sandelic et al.

Summary: Microgrids are a technology that can provide sustainable and efficient electrical energy solutions by utilizing distributed energy resources to supply local loads and improve network reliability. This paper discusses the importance of reliability-oriented design for microgrids that heavily rely on renewable energy-based, power electronics-interfaced distributed energy resources. The main areas of design improvements highlighted in this overview are the sizing and scheduling of distributed energy resources, as well as forecasting and optimization methods. The paper also emphasizes the need to include wear-out failure of power electronics in standard reliability assessment methods, as previous field experience has shown the adverse impact of such failures on power electronics-dominated systems. The findings of this paper provide a foundation for the development of new procedures for reliability-oriented design and planning of future, power electronics-dominated microgrids.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2022)

Review Engineering, Multidisciplinary

Policy and Management of Carbon Peaking and Carbon Neutrality: A Literature Review

Yi-Ming Wei et al.

Summary: This study comprehensively collates and investigates 1105 published research studies on carbon peaking and carbon neutrality, and summarizes the priorities and standpoints of key industries. The study also identifies the scientific concerns and strategic demands for achieving these two goals, providing theoretical insights and practical measures for China's carbon-neutral future. This research is crucial for policy formulation related to carbon peaking and carbon neutrality.

ENGINEERING (2022)

Article Automation & Control Systems

Detection of Malicious Attacks in Autonomous Cyber-Physical Inverter-Based Microgrids

Ioannis Zografopoulos et al.

Summary: This article investigates the detection of malicious cyber-physical attacks in multiagent microgrid (MG) systems based on subspace methods. The impact of the attack models and the feasibility of the developed detection method are demonstrated through simulation models of the Canadian urban benchmark distribution system.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Energy & Fuels

Double deepQ-learningcoordinated control of hybrid energy storage system in island micro-grid

Yunjun Yu et al.

Summary: This study focuses on using a hybrid energy storage system in island micro-grids to address energy demands, proposing the Double deep Q-learning algorithm for optimizing control strategies. Experimental results demonstrate the method's effectiveness in handling various weather conditions and increasing renewable energy utilization.

INTERNATIONAL JOURNAL OF ENERGY RESEARCH (2021)

Article Green & Sustainable Science & Technology

An advanced real-time dispatching strategy for a distributed energy system based on the reinforcement learning algorithm

Fanyi Meng et al.

Summary: This study explores optimal coordinated dispatch strategy for wind-thermal hybrid distribution systems by establishing a Markov decision process model to minimize operation and maintenance costs, utilizing Monte Carlo method and Q-learning algorithm for efficient evaluation. The proposed algorithm demonstrates high efficiency in solving real-time dispatching problems.

RENEWABLE ENERGY (2021)

Article Energy & Fuels

A storage expansion planning framework using reinforcement learning and simulation-based optimization

Stamatis Tsianikas et al.

Summary: In the highly electrified future, energy storage is crucial in areas with abundant distributed generation such as microgrids. Determining which storage technology to invest in, when, and how much capacity is becoming increasingly important. Future strategic planning and modern frameworks are needed to address these issues.

APPLIED ENERGY (2021)

Article Engineering, Electrical & Electronic

Resilience-Oriented DG Siting and Sizing Considering Stochastic Scenario Reduction

Qingxin Shi et al.

Summary: This study proposes a fuel-based distributed generator allocation strategy to enhance the distribution system resilience against extreme weather. It uses a two-stage stochastic mixed-integer programming model to make decisions under budget constraints and minimize operating costs in uncertain fault scenarios. The effectiveness of the algorithm is demonstrated through case studies on IEEE 33-bus and 123-bus test systems.

IEEE TRANSACTIONS ON POWER SYSTEMS (2021)

Article Engineering, Electrical & Electronic

Intelligent Multi-Microgrid Energy Management Based on Deep Neural Network and Model-Free Reinforcement Learning

Yan Du et al.

IEEE TRANSACTIONS ON SMART GRID (2020)

Article Engineering, Electrical & Electronic

Double Deep Q-Learning-Based Distributed Operation of Battery Energy Storage System Considering Uncertainties

Van-Hai Bui et al.

IEEE TRANSACTIONS ON SMART GRID (2020)

Article Green & Sustainable Science & Technology

Long-term sizing of rural microgrids: Accounting for load evolution through multi-step investment plan and stochastic optimization

Nicolo Stevanato et al.

ENERGY FOR SUSTAINABLE DEVELOPMENT (2020)

Article Computer Science, Information Systems

Prevention and Survivability for Power Distribution Resilience: A Multi-Criteria Renewables Expansion Model

Honggang Wang et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Residential Load Scheduling With Renewable Generation in the Smart Grid: A Reinforcement Learning Approach

T. Remani et al.

IEEE SYSTEMS JOURNAL (2019)

Article Engineering, Electrical & Electronic

Critical Load Restoration Using Distributed Energy Resources for Resilient Power Distribution System

Shiva Poudel et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2019)

Article Green & Sustainable Science & Technology

Economic and resilience benefit analysis of incorporating battery storage to photovoltaic array generation

Jian Zhou et al.

RENEWABLE ENERGY (2019)

Article Green & Sustainable Science & Technology

Optimal expansion planning of isolated microgrid with renewable energy resources and controllable loads

Zhaojian Wang et al.

IET RENEWABLE POWER GENERATION (2017)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)