Paper Title: Web-Based Federated Learning Predictive Analysis for Smart Grid Platform, 2024 — First author, Conference Paper, Published
Conference Name: KICS Fall 2024
Abstract: Abstract—This paper presents a novel web-based federated
learning framework to predict energy contract types based on
decentralized client data. By incorporating a central validation
dataset post-aggregation, the model improves its accuracy while
ensuring data privacy. A web application manages clients, al
lowing real-time monitoring, adding/removing participants, and
observing training performance. The aggregated global model
achieved an accuracy of 97%, demonstrating strong prediction
capabilities for specific contract types. This system offers a scal
able, privacy-preserving solution for energy contract optimiza
tion, contributing to the advancement of Smart grid management.