.png){kind=icon}
.png){kind=icon}
Return
Quantized deep learning model based Volt-Var control for hosting capacity maximization: a practical case study
.png){kind=icon}
OA
AI
DOI：10.1016/j.ijepes.2025.111524.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Development of a quantized 1D convolutional neural network (QCNN) model to emulate data driven Volt-Var control. • Post-training quantization (PTQ) is applied to reduce model size for real-world deployment on compact edge devices. • Proposing a novel Modified Reptile Search Algorithm (MRSA) for HC maximization. • Detailed hosting capacity analysis of the Sundom Smart Grid, a real-world grid located in Vaasa, Finland. • Investigating D-FCS-MPC based control framework for HC maximization while ensuring compliance with EN 50549 standards.
Keywords:
Hosting capacity (HC)
Modified Reptile search Algorithm (MRSA)
Quantized 1D Convolutional Neural Network (QCNN)
Decoupled Finite Control Set Model Predictive control (D-FCS-MPC)
Post-Training Quantization (PTQ)
and EN 50549 standard
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
5
Papers:
442
Citations:
0