Research on load frequency control of multi-microgrids in an isolated system based on the multi-agent soft actor-critic algorithm

Article Computer Science, Information Systems

A Frequency and Voltage Coordinated Control Strategy of Island Microgrid including Electric Vehicles

Peixiao Fan et al.

Summary: This paper proposes a comprehensive VF control strategy based on DDPG for an islanded microgrid with EVs, which can effectively suppress VF fluctuations caused by wind disturbance and load fluctuations.

ELECTRONICS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Proficient power control strategy for combined solar gas turbine-wind turbine generator-biodiesel generator based two area interconnected microgrid employed with DC link using Harris's hawk optimization optimised tilt-integral-derivative controller

Mausri Bhuyan et al.

Summary: This work presents a method for controlling the frequency in an independent double area interconnected hybrid microgrid system. The tilt-integral-derivative controller and Harris's hawk optimization technique are used to tune the parameters of the controllers, resulting in improved control performance.

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep learning, reinforcement learning, and world models

Yutaka Matsuo et al.

Summary: This review summarizes the talks and discussions on deep learning and reinforcement learning at the International Symposium on Artificial Intelligence and Brain Science. The review highlights the strong connections of DL and RL with brain functions and neuroscientific findings. The focus of the discussions is on whether comprehensive understanding of human intelligence can be achieved based on the recent advances in DL and RL algorithms, with speakers presenting their recent studies that could be key technologies for achieving human-level intelligence.

NEURAL NETWORKS (2022)

添加到收藏夹

Article Thermodynamics

Dynamic performance enhancement of interconnected hybrid thermal power system in the presence of electric vehicles

Niveditha Sivadanam et al.

Summary: The integration of non-synchronous distributed energy resources and energy storage systems into thermal grids affects the total synchronous inertia, which in turn impacts the frequency response of the electrical grid. The study proposes incorporating plug-in hybrid electric vehicles into load frequency control using a biogeography-based optimization algorithm. Results show that a virtual synchronous power-HVDC tie-link outperforms other tie-links in improving the frequency response, highlighting the role of EVs in enhancing dynamic performance.

CASE STUDIES IN THERMAL ENGINEERING (2021)

添加到收藏夹

Article Thermodynamics

A frequency control strategy for multimicrogrids with V2G based on the improved robust model predictive control

Yingqing Rao et al.

Summary: This paper presents a control method using electric vehicles to achieve stable operation of multimicrogrids, with simulation experiments to verify its effectiveness. The proposed method can effectively suppress frequency fluctuations, enhance system anti-interference capabilities.

ENERGY (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A deep reinforcement learning-based method applied for solving multi-agent defense and attack problems

Liwei Huang et al.

Summary: The paper discusses the important issue of multiagent defense and attack in the field of multi-agent cooperation, based on deep reinforcement learning algorithms, especially Multi-agent DDPG (MADDPG). By reconstructing and redefining the environment, experimental results show that learning with MADDPG can improve the decision-making abilities of agents better than other DRL models.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Proceedings Paper Engineering, Industrial

A Q-Learning Based Dynamic Event-Triggered Control for Load Frequency Regulation of Power Systems with Denial-of-Service Attacks

Pengcheng Chen et al.

Summary: This work introduces a novel Q-learning based dynamic event-triggered strategy for load frequency regulation, optimizing the threshold to reduce data transmission and maintain system performance.

PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE) (2021)

添加到收藏夹

Article Computer Science, Information Systems

Emergency Load Shedding Strategy for Microgrids Based on Dueling Deep Q-Learning

Can Wang et al.

Summary: This paper proposes a data-driven load shedding strategy for microgrids, which uses a contribution indicator and deep Q learning algorithm to make intelligent decisions for emergency load shedding under different scenarios. Simulation results show that the strategy improves the stability of power supply for important loads, reduces load shedding decision-making time, and minimizes frequency fluctuations.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence