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
Engineering, Electrical & Electronic
Haotian Liu et al.
Summary: In this paper, a novel bi-level off-policy reinforcement learning method is proposed to solve the Volt/Var control problem in active distribution networks (ADNs) without accurate system models. By defining a Bi-level Markov decision process and using separate agents for the slow and fast timescale sub-problems, the proposed method achieves stable and satisfactory optimization of both discrete and continuous devices in ADNs.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Jie Liu et al.
Summary: This article introduces a novel power injection priority optimization-based control strategy for a PMSG-based wind farm. The strategy aims to provide voltage support and mitigate frequency excursion caused by voltage dip during faults. The conventional fixed reactive power injection priority plan is replaced by an adaptive power injection priority plan in order to achieve this objective. The control problem is formulated as a multi-objective function optimization problem, where the power injection priority plan is calculated by minimizing the shortfall of WF active power and maximizing the reactive power injection of WF. Simulation results demonstrate the effectiveness of the proposed strategy in mitigating frequency excursion while complying with the voltage support requirement during faults.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2023)
Article
Green & Sustainable Science & Technology
Mohammad Mehdi Hosseini et al.
Summary: This paper proposes a model that combines deep reinforcement learning (DRL) with quadratic programming for distribution system restoration after major outages. The model uses a DRL-trained controller to determine optimal power dispatch of distributed energy resources and a grid-level quadratic programming problem to check grid constraints and perform restoration operation. The implementation of DRL using the SAC algorithm surpasses the Deep Deterministic Policy Gradient in continuous action spaces. Numerical studies on a test distribution system demonstrate that this hierarchical combination accelerates local operation and ensures network constraint satisfaction during restoration.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Green & Sustainable Science & Technology
Mohammad Mehdi Hosseini et al.
Summary: This paper proposes a model that combines deep reinforcement learning and mathematical optimization to operate distributed energy storage systems in distribution grids. By utilizing the fast response capability of deep reinforcement learning and keeping network constraints in check with mathematical optimization, the paper addresses the issues caused by load and renewable generation uncertainties.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Green & Sustainable Science & Technology
Mohammad Mehdi Hosseini et al.
Summary: This paper proposes a hierarchical combination model of deep reinforcement learning (DRL) and quadratic programming for distribution system restoration after major outages. DRL-trained controller determines optimal power dispatch of distributed energy resources, while grid-level quadratic programming checks grid constraints and performs critical restoration operation. Numerical studies show that this combined approach improves the speed of local operation and ensures network constraints satisfaction during restoration.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Green & Sustainable Science & Technology
Mohammad Mehdi Hosseini et al.
Summary: This paper proposes a model that combines deep reinforcement learning (DRL) and mathematical optimization for the operation of energy storage systems (ESS) in distribution grids. The model utilizes the fast response capability of DRL while maintaining network constraints, enabling efficient operation of ESS under uncertain load and renewable generation conditions.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Energy & Fuels
Wei Dong et al.
Summary: This paper proposes a data-driven method for renewable scenario creation by embedding interpretable features and controlling the generation process. The results demonstrate that the proposed approach can achieve controllable scenario generation with various statistical characteristics and create new generation patterns.
Article
Engineering, Electrical & Electronic
Yao Long et al.
Summary: This paper proposes a bi-level optimization framework for optimal Volt/VAR control in distribution networks. The upper-level determines the setpoints of mechanical devices to minimize network active power losses, while the lower-level represents the coordinated actions taken by inverters for their own objectives. The interactions between these two levels are captured using Karush-Kuhn-Tucker (KKT) conditions, allowing for cooperative optimization among different voltage regulation devices.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2022)
Article
Computer Science, Information Systems
Vijay Babu Pamshetti et al.
Summary: This article investigates the coordinated allocation of battery energy storage system (BESS) and soft open point (SOP) in high photovoltaic penetrated distribution network incorporating demand response (DR) and conservation voltage reduction (CVR) schemes. A two-stage coordinated optimization framework has been developed for integrated planning of BESS and SOP considering DR and CVR schemes. The proposed framework aims to minimize the total investment and operating cost of BESS and SOP devices, and it includes the cost of purchased power from substation, cost of energy not served, and cost of CO2 emission. A stochastic module and K-means clustering technique are adopted to address uncertainties related to PV generation and load demands. The test results demonstrate the effectiveness of the proposed framework in improving system efficiency, enhancing flexibility and reliability, and reducing carbon emission footprint.
IEEE SYSTEMS JOURNAL
(2022)
Article
Automation & Control Systems
Mohammad Mehdi Hosseini et al.
Summary: This article introduces an intelligent resilience controller (IRC) developed using deep reinforcement learning, which generates real-time operation decisions to dispatch distributed generation and energy storage units for power restoration after sudden outages. The proposed model successfully learns the failure development pattern of uncertain high-impact events and performs well in a simulated hurricane scenario with reduced operation costs and minimal running time.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Green & Sustainable Science & Technology
Cuo Zhang et al.
Summary: This paper proposes a three-stage hierarchically-coordinated VVC method considering network voltage stability to address voltage fluctuation and stability issues brought by intermittent photovoltaic power generation. The method optimizes control gains to reduce network power losses and bus voltage deviations while maintaining network voltage stability.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2022)
Article
Engineering, Multidisciplinary
Arunima Dutta et al.
Summary: This article proposes a model predictive-based voltage control method to optimize the coordination of power set points in distribution equipment and PV inverters for voltage stability in distribution networks. The study also explores the roles of demand response and conservation voltage reduction in improving energy efficiency.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Xin Chen et al.
Summary: This paper provides a comprehensive review of the application of reinforcement learning techniques in decision-making and control in power systems. It presents RL-based models and solutions in key application areas such as frequency regulation, voltage control, and energy management, and discusses critical issues and potential future directions in the application of RL.
IEEE TRANSACTIONS ON SMART GRID
(2022)
Article
Engineering, Electrical & Electronic
Hoang Tien Nguyen et al.
Summary: This paper presents a three-stage inverter-based framework for peak shaving and Volt-VAR control in active distribution systems. It utilizes the online safe deep reinforcement learning method to coordinate different control timescales and reduce peak load, voltage violations, and real power loss. The proposed method is efficient and safe, and its effectiveness is validated on IEEE 33-bus and IEEE 123-bus systems.
IEEE TRANSACTIONS ON SMART GRID
(2022)
Article
Green & Sustainable Science & Technology
Yuanhai Gao et al.
Summary: This article proposes a parameter estimation method for GMM with large component numbers and derives a closed-form solution for PPF calculation, validating the importance of large component numbers. The proposed uncertainty modeling method shows superiority in describing the details of wind power probability densities.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2022)
Proceedings Paper
Energy & Fuels
Soroush Najafi et al.
Summary: Increasing renewable energy penetration in distribution networks is challenging due to their intermittent nature. New tools are needed to deal with uncertainties and optimize grid operation. This paper proposes a second-order cone power flow model combined with chance constraint optimization for volt/VAR optimization in distribution networks, considering uncertainties introduced by loads and distributed energy resources. Experimental results on a modified 33-bus distribution system demonstrate the effectiveness of the proposed method in reducing total operation cost.
2022 IEEE KANSAS POWER AND ENERGY CONFERENCE (KPEC 2022)
(2022)
Article
Computer Science, Information Systems
Ali Soleimani et al.
Summary: This paper presents an Energy Management System (EMS) framework to extend the life of Battery Energy Systems (BES) connected to Renewable Energy Sources (RES) in an Active Distribution Network (ADN) by optimizing the techno-economic aspects. The proposed approach includes a linearized algorithm, a mixed-integer linear programming model, a two-stage stochastic programming method, and a linearized battery lifetime assessment.
Article
Green & Sustainable Science & Technology
Arsalan Najaji et al.
Summary: This paper proposes a stochastic-based decision-making framework for efficient management of smart energy hubs in power systems with high penetration of renewable energy, aiming to minimize the cost of electricity and heat energy carriers procurement in day-ahead and regulation markets.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Engineering, Electrical & Electronic
Yifei Guo et al.
Summary: This paper introduces a co-optimization framework that optimizes the cooperation between distributed generators, battery energy storage systems, and voltage regulating devices to achieve integrated peak shaving and voltage regulation in distribution grids.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2021)
Article
Automation & Control Systems
Yuefang Du et al.
Summary: The proposed approach introduces an adjustable uncertainty set to address uncertainties in renewable energy unit commitment, optimizing demand response to reduce operation risks of load shedding and RE curtailment. Without predefined parameters, it effectively transforms the original mixed-integer nonlinear problem into a mixed-integer linear problem for verification on IEEE systems. By comparing with existing methods, the effectiveness of the proposed approach in reducing conservativeness and operation risks is confirmed.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Electrical & Electronic
Mostafa Vahedipour-Dahraie et al.
Summary: This article discusses the optimal bidding strategy of a virtual power plant in various markets, as well as the behavior decisions of both the VPP and customers in providing reserve services and participating in demand response programs.
IEEE TRANSACTIONS ON SMART GRID
(2021)
Article
Engineering, Electrical & Electronic
Hangyue Liu et al.
Summary: Inverter-based Volt/Var control (VVC) methods are effective in addressing voltage deviations and power losses in distribution networks. This paper proposes a multi-region coordinated VVC optimization problem formulated as a partially observable Markov Game and solved using a modified multi-agent deep deterministic policy gradient (MADDPG) algorithm. The algorithm can handle uncertainties in photovoltaic power generation and loads, ensuring robustness in the solution.
IEEE TRANSACTIONS ON SMART GRID
(2021)
Article
Green & Sustainable Science & Technology
Yang Li et al.
Summary: This study establishes a bi-level optimal dispatching model to balance the interests between CIES and EVCS by coordinating flexible demand response and uncertain renewables.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2021)
Article
Engineering, Multidisciplinary
Vijay Babu Pamshetti et al.
Summary: The article introduces a multistage coordinated CVR methodology incorporating IDG and SOP devices for offline and online studies, and validates the effectiveness of the method through case studies and tests on sudden external disturbances.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Subho Paul et al.
Summary: This article discusses the necessity of deploying hybrid ac/dc distribution networks in the conventional ac network with increasing penetration of dc resources and loads. A new risk constrained energy efficient management algorithm is proposed for minimizing energy costs under uncertain parameters such as solar power generation and load demand. Simulations show the effectiveness of the proposed technique in achieving optimal energy efficiency.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Adel Heidari-Akhijahani et al.
Summary: A realistic and practicable unbalanced linear three-phase four-wire power flow model is proposed in this letter, which is based on current injection equations at nodes and considers the ZIP representation for loads. The model can be easily applied to unbalanced three-wire networks with minor changes and assumptions, covering both low-voltage and medium-voltage distribution networks. The performance of the proposed model is verified through simulations on two IEEE test feeders.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Yuanqi Gao et al.
Summary: This study proposes a consensus multi-agent deep reinforcement learning algorithm to solve the Volt-VAR control problem, enabling individual agents to learn a group control policy using local rewards. Numerical studies show that the proposed algorithm matches the performance of single-agent reinforcement learning benchmarks and is communication efficient and resilient.
IEEE TRANSACTIONS ON SMART GRID
(2021)
Proceedings Paper
Energy & Fuels
Mohammad MansourLakouraj et al.
Summary: This paper proposes a MILP risk-averse stochastic optimization model to co-optimize traditional devices and solar photovoltaics along with energy storage systems in distribution grids. The Conservation Voltage Reduction (CVR) is integrated into the framework to reduce load energy consumption. Gaussian Mixture Model (GMM) and unsupervised fuzzy k-means method are used to handle uncertainty in PV generation.
2022 IEEE TEXAS POWER AND ENERGY CONFERENCE (TPEC)
(2021)
Proceedings Paper
Computer Science, Theory & Methods
Mohammad MansourLakouraj et al.
Summary: A multi-timescale Volt/VAR control model is proposed in this study to optimize traditional capacitor banks with PV and EV inverters. By coordinating resources between different time scales, the model addresses prediction errors in PV generation and the impact of weather-related changes on power systems.
2021 IEEE PES INNOVATIVE SMART GRID TECHNOLOGY EUROPE (ISGT EUROPE 2021)
(2021)
Article
Computer Science, Information Systems
Zohreh S. Hosseini et al.
Summary: This paper focuses on a comprehensive study, modeling, simulation, and comparison of Conservation Voltage Reduction (CVR) and Volt-VAR Optimization (VVO) programs in electric utilities, and examines the sensitivity of various CVR Measurement and Verification (M&V) methodologies to data anomaly issues.
Article
Computer Science, Information Systems
Panggah Prabawa et al.
Summary: This study proposes a hierarchical Volt-VAR optimization framework for smart electric vehicle charging stations equipped with distributed energy resources, aiming to maintain voltage quality in power distribution networks. The framework consists of global and local voltage control stages, utilizing smart inverters to regulate voltage. Simulation results demonstrate the framework's effectiveness in reducing power losses, optimizing voltage control, and meeting probability constraints.
Article
Green & Sustainable Science & Technology
Md Shakawat Hossan et al.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2020)
Article
Engineering, Electrical & Electronic
Cuo Zhang et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Proceedings Paper
Energy & Fuels
Amin Khodaei et al.
2020 IEEE/PES TRANSMISSION AND DISTRIBUTION CONFERENCE AND EXPOSITION (T&D)
(2020)
Article
Engineering, Electrical & Electronic
Rahul R. Jha et al.
Article
Computer Science, Information Systems
Argo Rosin et al.
Article
Engineering, Electrical & Electronic
Firdous Ul Nazir et al.
IEEE TRANSACTIONS ON SMART GRID
(2020)
Article
Engineering, Electrical & Electronic
Cuo Zhang et al.
IEEE TRANSACTIONS ON SMART GRID
(2019)
Article
Thermodynamics
Mohammad Mansour-lakouraj et al.
Article
Engineering, Electrical & Electronic
Rabih A. Jabr
IEEE TRANSACTIONS ON POWER SYSTEMS
(2018)
Article
Green & Sustainable Science & Technology
Xin Chen et al.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2018)
Article
Engineering, Electrical & Electronic
Mohammad H. Shams et al.
ELECTRIC POWER SYSTEMS RESEARCH
(2018)
Article
Engineering, Electrical & Electronic
Yunfeng Wen et al.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2016)
Article
Engineering, Electrical & Electronic
Amin Khodaei
IEEE TRANSACTIONS ON POWER SYSTEMS
(2014)
Article
Engineering, Electrical & Electronic
Amir Safdarian et al.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2013)
Article
Engineering, Electrical & Electronic
Ravindra Singh et al.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2010)
Article
Engineering, Electrical & Electronic
Masood Parvania et al.
IEEE TRANSACTIONS ON SMART GRID
(2010)
Article
Engineering, Electrical & Electronic
Ferry A. Viawan et al.
IEEE TRANSACTIONS ON POWER DELIVERY
(2008)
Article
Computer Science, Software Engineering
J Dupacová et al.
MATHEMATICAL PROGRAMMING
(2003)
