activity
20212024
most citedFederated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients

2 citations · 6 across the 10 of their papers we have counts for

collaborators

10 papers

cs.LG20242 cited

Addressing Heterogeneity in Federated Load Forecasting with Personalization Layers

Shourya Bose, Yu Zhang, Kibaek Kim

The advent of smart meters has enabled pervasive collection of energy consumption data for training short-term load forecasting models. In response to privacy concerns, federated l…

cs.DC2024

Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources -- A Case Study on Federated Fine-tuning of LLaMA 2

Zilinghan Li, Shilan He, Pranshu Chaturvedi +4

Federated learning enables multiple data owners to collaboratively train robust machine learning models without transferring large or sensitive local datasets by only sharing the p…

math.OC2023

On Solving Unit Commitment with Alternating Current Optimal Power Flow on GPU

Weiqi Zhang, Youngdae Kim, Kibaek Kim

We consider the unit commitment (UC) problem that employs the alternating current optimal power flow (ACOPF) constraints, which is formulated as a mixed-integer nonlinear programmi…

math.OC20231 cited

GPU-Accelerated Sequential Quadratic Programming Algorithm for Solving ACOPF

Bowen Li, Michel Schanen, Kibaek Kim

Sequential quadratic programming (SQP) is widely used in solving nonlinear optimization problem, with advantages of warm-starting solutions, as well as finding high-accurate soluti…

math.OC2023

A GPU-based Distributed Algorithm for Linearized Optimal Power Flow in Distribution Systems

Minseok Ryu, Geunyeong Byeon, Kibaek Kim

We propose a GPU-based distributed optimization algorithm, aimed at controlling optimal power flow in multi-phase and unbalanced distribution systems. Typically, conventional distr…

cs.LG20232 cited

Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients

Shourya Bose, Kibaek Kim

The advent of smart meters has enabled pervasive collection of energy consumption data for training short-term load forecasting (STLF) models. In response to privacy concerns, fede…