Technology Category
Cognitive Modeling & Cognitive Systems: Adaptive BehaviorIntelligent Robots: State EstimationMultiagent Systems: Adversarial Agents
Frequency Control in Microgrids: An Adaptive Fuzzy-Neural-Network Virtual Synchronous Generator
🤖 AI Summary
To address deteriorating frequency stability in microgrids caused by reduced inertia and damping under high renewable energy penetration, this paper proposes a virtual synchronous generator (VSG) frequency control strategy based on an adaptive fuzzy neural network (AFNN). The method dynamically adjusts virtual inertia, damping, and droop coefficients online, overcoming the adaptability limitations of conventional fixed-parameter VSGs. Its key innovation lies in synergistically integrating the interpretability of fuzzy logic with the online learning capability of neural networks to achieve autonomous, real-time parameter optimization. Validated via MATLAB/Simulink simulation and hardware-in-the-loop testing on an ARM Cortex-M3 (SAM3X8E) platform, the proposed approach achieves a maximum frequency deviation of ≤0.03 Hz. It significantly outperforms conventional VSG and fuzzy-based controllers in both settling time and recovery speed, thereby enhancing system robustness against renewable power fluctuations and improving overall frequency regulation performance.
Technology Category
Application Category
📝 Abstract
The reliance on distributed renewable energy has increased recently. As a result, power electronic-based distributed generators replaced synchronous generators which led to a change in the dynamic characteristics of the microgrid. Most critically, they reduced system inertia and damping. Virtual synchronous generators emulated in power electronics, which mimic the dynamic behaviour of synchronous generators, are meant to fix this problem. However, fixed virtual synchronous generator parameters cannot guarantee a frequency regulation within the acceptable tolerance range. Conversely, a dynamic adjustment of these virtual parameters promises robust solution with stable frequency. This paper proposes a method to adapt the inertia, damping, and droop parameters dynamically through a fuzzy neural network controller. This controller trains itself online to choose appropriate values for these virtual parameters. The proposed method can be applied to a typical AC microgrid by considering the penetration and impact of renewable energy sources. We study the system in a MATLAB/Simulink model and validate it experimentally in real time using hardware-in-the-loop based on an embedded ARM system (SAM3X8E, Cortex-M3). Compared to traditional and fuzzy logic controller methods, the results demonstrate that the proposed method significantly reduces the frequency deviation to less than 0.03 Hz and shortens the stabilizing/recovery time.
Problem
Research questions and friction points this paper is trying to address.
Addressing reduced inertia in microgrids with renewable energy
Dynamic adjustment of virtual synchronous generator parameters
Minimizing frequency deviation and recovery time
Innovation
Methods, ideas, or system contributions that make the work stand out.
Adaptive fuzzy-neural-network for dynamic parameter adjustment
Online self-training controller for virtual synchronous generators
Hardware-in-the-loop validation with ARM Cortex-M3
🔎 Similar Papers
No similar papers found.
