Robust Artificial Intelligence Controller for Stabilization of Full-Bridge Converters Feeding Constant Power Loads

Article Engineering, Electrical & Electronic

Stabilization of 5G Telecom Converter-Based Deep Type-3 Fuzzy Machine Learning Control for Telecom Applications

Meysam Gheisarnejad et al.

Summary: This study presents an adaptive interval type-3 fuzzy logic system (IT3-FLS) employing deep reinforcement learning (DRL) to achieve voltage stabilization in the 5G-telecom power system (5G-TPS). Hardware-in-the-Loop (HiL) testing on an OPAL-RT platform is conducted to validate the effectiveness of the proposed adaptive IT3-FLS method.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Stabilization of DC-DC buck converter with unknown constant power load via passivity-based control plus proportion-integration

Wei He et al.

Summary: This paper proposed a new control algorithm for DC-DC buck converter feeding unknown CPL, using a combination of PBC and PI to reshape system energy and improve disturbance rejection performance, and developing a parameter estimation algorithm based on I&I technique to estimate the extracted power load online, leading to an adaptive strategy implementation. The stability analysis of the cascaded system, including closed-loop control system and observer error dynamics, was conducted to validate the performance of the proposed controller through simulation and experimental results.

IET POWER ELECTRONICS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

False Data Injection Cyber-Attacks Mitigation in Parallel DC/DC Converters Based on Artificial Neural Networks

Mohammad Reza Habibi et al.

Summary: DC microgrids are vulnerable to false data injection attacks (FDIAs), and this study discusses the impact of such attacks and introduces a strategy based on artificial neural networks to eliminate them.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS (2021)

Add to Collection

Article Automation & Control Systems

Battery Thermal- and Health-Constrained Energy Management for Hybrid Electric Bus Based on Soft Actor-Critic DRL Algorithm

Jingda Wu et al.

Summary: This article presents a novel knowledge-based, multiphysics-constrained energy management strategy for hybrid electric buses, focusing on thermal safety and degradation of onboard lithium-ion battery system. The strategy utilizes a multiconstrained least costly formulation and soft actor-critic deep reinforcement learning to optimize power allocation. Tests show its superiority in terms of converging effort, enforcement of battery safety, and reduction of driving cost.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Energy & Fuels

Load Frequency Active Disturbance Rejection Control for Multi-Source Power System Based on Soft Actor-Critic

Yuemin Zheng et al.

Summary: A study on addressing load disturbances in power systems using linear active disturbance rejection control (LADRC) based on tie-line bias control mode and Soft Actor-Critic algorithm in reinforcement learning for real-time adjustment of controller parameters shows significant advantages in terms of overshoot, undershoot, and settling time compared to other proportional-integral-derivative control techniques and LADRC with constant parameters.

ENERGIES (2021)

Add to Collection

Article Engineering, Electrical & Electronic