Search Results for author: Dejan Vukobratovic

Found 12 papers, 4 papers with code

A Weighted Autoencoder-Based Approach to Downlink NOMA Constellation Design

no code implementations23 Jun 2023 Vukan Ninkovic, Dejan Vukobratovic, Adriano Pastore, Carles Anton-Haro

End-to-end design of communication systems using deep autoencoders (AEs) is gaining attention due to its flexibility and excellent performance.

Graph Neural Networks on Factor Graphs for Robust, Fast, and Scalable Linear State Estimation with PMUs

no code implementations28 Apr 2023 Ognjen Kundacina, Mirsad Cosovic, Dragisa Miskovic, Dejan Vukobratovic

As phasor measurement units (PMUs) become more widely used in transmission power systems, a fast state estimation (SE) algorithm that can take advantage of their high sample rates is needed.

Supporting Future Electrical Utilities: Using Deep Learning Methods in EMS and DMS Algorithms

no code implementations1 Mar 2023 Ognjen Kundacina, Gorana Gojic, Mile Mitrovic, Dragisa Miskovic, Dejan Vukobratovic

Electrical power systems are increasing in size, complexity, as well as dynamics due to the growing integration of renewable energy resources, which have sporadic power generation.

energy management Management

Scalability and Sample Efficiency Analysis of Graph Neural Networks for Power System State Estimation

no code implementations28 Feb 2023 Ognjen Kundacina, Gorana Gojic, Mirsad Cosovic, Dragisa Miskovic, Dejan Vukobratovic

Additionally, to evaluate the scalability of the GNN model, we conduct experiments on power systems of various sizes.

Rateless Autoencoder Codes: Trading off Decoding Delay and Reliability

no code implementations28 Jan 2023 Vukan Ninkovic, Dejan Vukobratovic, Christian Häger, Henk Wymeersch, Alexandre Graell i Amat

Most of today's communication systems are designed to target reliable message recovery after receiving the entire encoded message (codeword).

Distributed Nonlinear State Estimation in Electric Power Systems using Graph Neural Networks

1 code implementation23 Jul 2022 Ognjen Kundacina, Mirsad Cosovic, Dragisa Miskovic, Dejan Vukobratovic

Nonlinear state estimation (SE), with the goal of estimating complex bus voltages based on all types of measurements available in the power system, is usually solved using the iterative Gauss-Newton method.

Near Real-Time Distributed State Estimation via AI/ML-Empowered 5G Networks

no code implementations22 Jul 2022 Ognjen Kundacina, Miodrag Forcan, Mirsad Cosovic, Darijo Raca, Merim Dzaferagic, Dragisa Miskovic, Mirjana Maksimovic, Dejan Vukobratovic

Firstly, in a tutorial fashion, we present an overview on how distributed SE can be integrated with the elements of the 5G core network and radio access network architecture.

energy management Management

Robust and Fast Data-Driven Power System State Estimator Using Graph Neural Networks

1 code implementation6 Jun 2022 Ognjen Kundacina, Mirsad Cosovic, Dejan Vukobratovic

The power system state estimation (SE) algorithm estimates the complex bus voltages based on the available set of measurements.

State Estimation in Electric Power Systems Leveraging Graph Neural Networks

1 code implementation11 Jan 2022 Ognjen Kundacina, Mirsad Cosovic, Dejan Vukobratovic

The goal of the state estimation (SE) algorithm is to estimate complex bus voltages as state variables based on the available set of measurements in the power system.

Deep Learning Anomaly Detection for Cellular IoT with Applications in Smart Logistics

no code implementations17 Feb 2021 Milos Savic, Milan Lukic, Dragan Danilovic, Zarko Bodroski, Dragana Bajovic, Ivan Mezei, Dejan Vukobratovic, Srdjan Skrbic, Dusan Jakovetic

The number of connected Internet of Things (IoT) devices within cyber-physical infrastructure systems grows at an increasing rate.

Anomaly Detection Networking and Internet Architecture

Preamble-Based Packet Detection in Wi-Fi: A Deep Learning Approach

no code implementations12 Sep 2020 Vukan Ninkovic, Dejan Vukobratovic, Aleksandar Valka, Dejan Dumic

Wi-Fi systems based on the family of IEEE 802. 11 standards that operate in unlicenced bands are the most popular wireless interfaces that use Listen Before Talk (LBT) methodology for channel access.

Distributed Gauss-Newton Method for State Estimation Using Belief Propagation

4 code implementations19 Feb 2017 Mirsad Cosovic, Dejan Vukobratovic

We present a novel distributed Gauss-Newton method for the non-linear state estimation (SE) model based on a probabilistic inference method called belief propagation (BP).

Information Theory Information Theory Optimization and Control

Cannot find the paper you are looking for? You can Submit a new open access paper.