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。
Article
Green & Sustainable Science & Technology
Yongqiang Tan et al.
Summary: To implement the national strategies for carbon emission reduction, reforms are needed in the electric power industries to address challenges of decarbonization, marketization, and energy transition. A scheduling framework that considers low-carbon demand and economic cost has been proposed, along with an improved deep reinforcement learning-based algorithm to solve the problem of low-carbon economic dispatch. The results show significant improvements in profits and reductions in carbon emissions.
IET RENEWABLE POWER GENERATION
(2023)
Article
Construction & Building Technology
Yonghong Zhu et al.
Summary: This study presents a novel risk-based multi-objective energy exchange optimization for microgrids, considering the inherent volatility and unpredictable nature of renewable resources and load demand uncertainties. Three different risk-based strategies are distinguished using the conditional value at risk approach. The proposed model minimizes operation and maintenance costs, power exchange costs, power loss costs, and the amount of energy not supplied. A stochastic scenario-based approach and scenario reduction method are incorporated to control uncertainties. The proposed algorithm effectively improves local and global search and uses a fuzzy model for selecting the optimal solution.
SUSTAINABLE CITIES AND SOCIETY
(2023)
Article
Engineering, Electrical & Electronic
Enrique Gabriel Vera et al.
Summary: This study presents a Two Stage Stochastic Programming (TSSP) model for the planning of Multi-Microgrids (MMGs) in Active Distribution Networks (ADNs). The model aims to minimize total costs while taking advantage of Microgrids' interconnections and considering uncertainties in electricity demand and Renewable Energy Sources (RESs). The model uses Geometric Brownian Motion (GBM) and probability distribution functions (pdfs) to analyze associated uncertainties. It includes long-term purchase decisions, short-term operational constraints, and Geographical Information Systems (GIS) to realistically estimate rooftop solar limits. The TSSP model proves to be less conservative and faster with higher accuracy compared to a deterministic planning model and a Stochastic Linear Programming (SLP) algorithm.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Automation & Control Systems
Nicola Mignoni et al.
Summary: This paper investigates the control problem in energy communities and proposes two novel resolution algorithms. The effectiveness of these methods is validated through numerical simulations and compared with a centralized control method, showing better computational results.
CONTROL ENGINEERING PRACTICE
(2023)
Article
Engineering, Electrical & Electronic
Xueping Li et al.
Summary: This paper proposes a cloud-edge computing method for economic dispatch of active distribution network with multi-microgrids, aiming to address the risks and challenges of privacy data leakage and communication burden in traditional economic dispatch. The cloud server is responsible for the calculation of the active distribution network, while each edge server handles its own microgrid calculation. Through case analysis, the reliability of the cloud-edge computing method is confirmed. Simulation results demonstrate that the proposed method can provide a high-quality solution for economic dispatch of active distribution network with multi-microgrids while ensuring data privacy protection and reducing communication burden.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Nikita Tomin et al.
Summary: Energy communities are a successful model of local energy systems based on distributed energy sources and flexible electricity consumers. They serve as platforms for experiments in new energy practices, such as local markets for flexibility and cooperative microgrids, aiming to achieve energy autonomy. This work presents a unified approach to building and managing community microgrids, using bilevel programming and reinforcement learning. Numerical results show significant reduction in the LCOE index and improved electricity supply quality in real test cases.
Article
Automation & Control Systems
Paolo Scarabaggio et al.
Summary: A novel noncooperative control mechanism is proposed to optimize the operation of power distribution networks. By incorporating economic factors, physical constraints, and grid stability aspects, the mechanism leverages the flexible demand, dispatchable generation capability, and energy storage potential of active users to increase the penetration of renewable energy and improve the predictability of power injection from the high-voltage grid.
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS
(2022)
Article
Energy & Fuels
Imen Jendoubi et al.
Summary: With the ongoing energy transition, electric power and energy systems are becoming increasingly multi-dimensional and complex with higher levels of uncertainty. Reinforcement learning provides a data-driven alternative to traditional model-based control methods, allowing efficient control of such systems without prior system dynamics modeling or predictions. This study proposes a multi-agent deep reinforcement learning-based control framework for solving multi-dimensional power dispatch problems in systems with multiple uncertainties.
SUSTAINABLE ENERGY GRIDS & NETWORKS
(2022)
Article
Engineering, Electrical & Electronic
Daner Hu et al.
Summary: This paper proposes a hybrid voltage control strategy based on a mixed-integer optimization method and multi-agent reinforcement learning to optimize active and reactive power at both slow and fast timescales, effectively mitigating voltage fluctuations.
IEEE TRANSACTIONS ON SMART GRID
(2022)
Article
Automation & Control Systems
Bo Gu et al.
Summary: In this article, the competitive interactions between a sensing platform (SP) and mobile users (MUs) in mobile crowdsensing (MCS) services are studied using a multistage Stackelberg game model, and a pricing strategy optimization method based on multiagent deep reinforcement learning algorithm is proposed. The efficiency of the proposed method is demonstrated through simulation results.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Energy & Fuels
Yuwei Shang et al.
Article
Engineering, Electrical & Electronic
Yan Du et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Article
Engineering, Electrical & Electronic
Yujian Ye et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Article
Engineering, Electrical & Electronic
Yujian Ye et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Article
Engineering, Electrical & Electronic
Yu Zhang et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Engineering, Electrical & Electronic
Yanchang Liang et al.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2020)
Article
Engineering, Electrical & Electronic
Esmat Samadi et al.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2020)
Article
Energy & Fuels
Haochen Hua et al.
Article
Automation & Control Systems
Mengqi Yao et al.
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS
(2019)
Article
Green & Sustainable Science & Technology
Karunakaran Venkatesan et al.
JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY
(2019)
Article
Energy & Fuels
Yu Zheng et al.
IEEE TRANSACTIONS ON ENERGY CONVERSION
(2018)
Article
Engineering, Electrical & Electronic
Elham Foruzan et al.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2018)