4.5 Article

Rolling horizon wind-thermal unit commitment optimization based on deep reinforcement learning

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Developing a hybrid probabilistic model for short-term wind speed forecasting

Xiaobo Zhang

Summary: This paper develops a hybrid versatile forecasting framework that provides detailed information about future wind speed uncertainty and demonstrates its value in the decision-making process of wind power operation and management through experiments.

APPLIED INTELLIGENCE (2023)

Article Computer Science, Artificial Intelligence

Time series cross-correlation network for wind power prediction

Ruiguo Yu et al.

Summary: This paper proposes a TSCN-LSTM model for wind power generation prediction, which accurately predicts wind power generation after 30 minutes. By integrating temporal and spatial feature extraction and enhancing timing and spatial relationships, this model efficiently explores the relevant information in wind power data.

APPLIED INTELLIGENCE (2023)

Article Engineering, Electrical & Electronic

Reduction method for multi-period time series scenarios of wind power

Ye He et al.

Summary: In the planning and operation of power systems with wind power, it is important to accurately represent the stochastic characteristics of wind power using a small number of representative time series scenarios. However, balancing computational efficiency and accuracy becomes challenging with an increasing number of scenarios. This study proposes a bi-directional optimization method to generate daily wind power time series scenarios by combining a single-period optimal scenario generation strategy and a multi-period scenario reduction strategy. The effectiveness and practicality of this method are verified through simulations.

ELECTRIC POWER SYSTEMS RESEARCH (2023)

Article Operations Research & Management Science

Tactical level strategies for multi-objective disassembly line balancing problem with multi-manned stations: an optimization model and solution approaches

Omer Faruk Yilmaz et al.

Summary: This study explores a multi-objective disassembly line balancing problem from a different point of view and proposes a novel multi-objective optimization model, achieving high-quality solutions with a group-based worker assignment strategy.

ANNALS OF OPERATIONS RESEARCH (2022)

Article Computer Science, Artificial Intelligence

Semi-supervised deep learning recognition method for the new classes of faults in wind turbine system

Jun Liu et al.

Summary: Traditional fault recognition algorithms can only identify known classes of fault in wind turbine systems. This study proposes a new method based on semi-supervised deep learning, which can effectively identify new class faults with higher accuracy compared to traditional methods.

APPLIED INTELLIGENCE (2022)

Article Engineering, Electrical & Electronic

A novel cooperative multi-search benders decomposition for solving the hydrothermal unit-commitment problem

Bruno Colonetti et al.

Summary: The paper introduces a cooperative multi-search Benders decomposition approach to solve the deterministic hydrothermal unit commitment (HTUC) problem, which is a primal method and solves subproblems in parallel, achieving over 15 times faster than the commercial solver Gurobi and solving HTUC problems with a gap of 0.1% in under 20 minutes.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Article Engineering, Electrical & Electronic

New metaheuristic methodology for solving security constrained hydrothermal unit commitment based on adaptive genetic algorithm

Borce Postolov et al.

Summary: A new metaheuristic technique based on genetic algorithm, adaptive strategy, and constraint handling repair mechanisms is proposed for solving Security Constrained Hydrothermal Unit Commitment (SCHTUC). The proposed technique is shown to be efficient on an IEEE 30 BUS test system with various constraints, outperforming other optimization methods such as DA-PSO and PSO-GWO.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Article Computer Science, Information Systems

Policy Iteration Reinforcement Learning-based control using a Grey Wolf Optimizer algorithm

Iuliu Alexandru Zamfirache et al.

Summary: This paper introduces a RL-based control approach using PI and GWO algorithm to train NNs, which shows better performance in the experiments.

INFORMATION SCIENCES (2022)

Article Green & Sustainable Science & Technology

Forecasting methods for wind power scenarios of multiple wind farms based on spatio-temporal dependency structure

Yanting Li et al.

Summary: This paper proposed a new wind power generation scheme for multiple wind farms that considers both spatial and temporal dependence of wind power time series in an efficient way based on copula theory. Different vine copulas were studied and compared, and a novel two-stage spatio-temporal sampling method was used to generate wind power scenario samples. The proposed conditional quantile sampling method can convert samples into specific wind power generation scenarios with more accuracy and efficiency.

RENEWABLE ENERGY (2022)

Article Engineering, Electrical & Electronic

Stochastic Optimal Operation Framework of an Integrated Methane-Based Zero-CO2 Energy Hub in Energy Markets

Alireza Tavakoli et al.

Summary: This paper presents a new structure of an energy hub that participates in electricity, heat, and natural gas energy markets by converting biomass fuel into valuable methane fuel. The paper proposes an optimal bidding framework and a deep learning model for scenario generation. The energy hub is profitable, flexible, environmentally friendly, and accurate in uncertainty modeling, and does not require the purchase of energy carriers.

ELECTRIC POWER SYSTEMS RESEARCH (2022)

Article Thermodynamics

Generalization ability of hybrid electric vehicle energy management strategy based on reinforcement learning method

Chunyang Qi et al.

Summary: This paper investigates the generalization capability of energy management strategies for hybrid electric vehicles and proposes a multi-agent reinforcement learning algorithm. By analyzing typical features and using an auxiliary agent, the generalization performance of energy management strategies is improved.

ENERGY (2022)

Article Computer Science, Information Systems

Simultaneous task and energy planning using deep reinforcement learning

Di Wang et al.

Summary: To improve energy awareness of unmanned autonomous vehicles, the paper proposes a combinatorial optimization model for simultaneous task and energy planning. A neural combinatorial optimizer is introduced to obtain fast and reliable near-optimal solutions, outperforming exact and heuristic algorithms in terms of computational cost.

INFORMATION SCIENCES (2022)

Article Automation & Control Systems

Retarded Sampled-Data Control Design for Interconnected Power System With DFIG-Based Wind Farm: LMI Approach

Raghul Venkateswaran et al.

Summary: This article investigates the robust stabilization of an interconnected power system with a DFIG-based wind farm using retarded sampled-data control (RSDC). A more general sampled-data control strategy involving constant time delay and varying sampling period is considered, with disturbances attenuated using an H infinity performance-based RSDC scheme. The proposed closed-loop system is proven to be asymptotically stable under the designed controller, as shown in simulation results.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Article Thermodynamics

Strategic bidding in a competitive electricity market: An intelligent method using Multi-Agent Transfer Learning based on reinforcement learning

Jiahui Wu et al.

Summary: This study proposes an intelligent strategic bidding theoretical framework using MATL and investigates four MATL algorithms. The performance of the intelligent bidding simulation model based on the four MATL algorithms is compared and analyzed from the perspective of accuracy and convergence speed. Furthermore, the rationality and effectiveness of the intelligent bidding method using MATL based on MARL are validated through case examples.

ENERGY (2022)

Article Automation & Control Systems

Scenario-oriented hybrid particle swarm optimization algorithm for robust economic dispatch of power system with wind power

Wang Bing et al.

Summary: This paper discusses the economic dispatch problem for power system with wind power, proposes a robust economic dispatch model based on discrete scenarios and bad scenario set, and achieves superior computational results through a hybrid particle swarm optimization (PSO) algorithm in experiments.

JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS (2022)

Article Engineering, Electrical & Electronic

Virtual-Action-Based Coordinated Reinforcement Learning for Distributed Economic Dispatch

Dewen Li et al.

Summary: The study presents a unified distributed RL solution for both static and dynamic economic dispatch problems, using a projection method to generate feasible actual actions. Distributed Hysteretic Q-learning coordinates agents effectively, while the algorithm handles continuous action space and power loads without using function approximations. Theoretical analysis and comparative simulation studies demonstrate the algorithm's convergence and optimality.

IEEE TRANSACTIONS ON POWER SYSTEMS (2021)

Article Computer Science, Artificial Intelligence

Feature selection and hyper parameters optimization for short-term wind power forecast

Hui Huang et al.

Summary: The study proposed a hybrid wind power forecasting model based on data preprocessing, modified Bayesian optimization algorithm, and gradient boosted regression trees approach. Case studies showed that the model outperformed contrasted models, indicating its potential in enhancing prediction accuracy and computation efficiency.

APPLIED INTELLIGENCE (2021)

Review Engineering, Electrical & Electronic

Solving stochastic hydrothermal unit commitment with a new primal recovery technique based on Lagrangian solutions

Murilo Reolon Scuzziato et al.

Summary: The study introduces a two-stage stochastic model for SHUC, solving the dual problem with LR method and obtaining the primal-feasible solution through Benders' Decomposition. Results demonstrate the advantage of primal recovery technique over MILP solver in solving large-scale problems.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Article Computer Science, Information Systems

Deep Reinforcement Learning for Scenario-Based Robust Economic Dispatch Strategy in Internet of Energy

Dawei Fang et al.

Summary: The article proposes a scenario-based robust economic dispatch strategy for virtual power plants, which effectively reduces operational costs through data augmentation and deep reinforcement learning to solve complex economic dispatch problems in virtual power plants.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Automation & Control Systems

Distributed Reinforcement Learning Algorithm for Dynamic Economic Dispatch With Unknown Generation Cost Functions

Pengcheng Dai et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Article Computer Science, Artificial Intelligence

Ultra-Scalable Spectral Clustering and Ensemble Clustering

Dong Huang et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

Article Engineering, Electrical & Electronic

Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning

Qiuling Yang et al.

IEEE TRANSACTIONS ON SMART GRID (2020)

Article Engineering, Electrical & Electronic

Real-Time Optimal Power Flow: A Lagrangian Based Deep Reinforcement Learning Approach

Ziming Yan et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

A bibliometric analysis on deep learning during 2007-2019

Yang Li et al.

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2020)

Article Automation & Control Systems

Distributed Q-Learning-Based Online Optimization Algorithm for Unit Commitment and Dispatch in Smart Grid

Fangyuan Li et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Article Engineering, Electrical & Electronic

Forecasted Scenarios of Regional Wind Farms Based on Regular Vine Copulas

Zhao Wang et al.

JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY (2020)

Article Engineering, Electrical & Electronic

Multistage Stochastic Unit Commitment Using Stochastic Dual Dynamic Integer Programming

Jikai Zou et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2019)

Article Engineering, Electrical & Electronic

A New Clustering Approach for Scenario Reduction in Multi-Stochastic Variable Programming

Jinxing Hu et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2019)

Article Computer Science, Artificial Intelligence

Optimal generation scheduling and dispatch of thermal generating units considering impact of wind penetration using hGWO-RES algorithm

Ashutosh Bhadoria et al.

APPLIED INTELLIGENCE (2019)

Article Engineering, Chemical

A rolling horizon approach for optimal management of microgrids under stochastic uncertainty

Javier Silvente et al.

CHEMICAL ENGINEERING RESEARCH & DESIGN (2018)

Article Engineering, Electrical & Electronic

Storage management by rolling stochastic unit commitment for high renewable energy penetration

Emmanouil A. Bakirtzis et al.

ELECTRIC POWER SYSTEMS RESEARCH (2018)

Article Engineering, Electrical & Electronic

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Yize Chen et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2018)

Article Computer Science, Artificial Intelligence

Distributed Economic Dispatch in Microgrids Based on Cooperative Reinforcement Learning

Weirong Liu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

Article Engineering, Electrical & Electronic

Two-Stage Multi-Objective Unit Commitment Optimization Under Hybrid Uncertainties

Bo Wang et al.

IEEE TRANSACTIONS ON POWER SYSTEMS (2016)