mec

for mass exploiting

A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning (DRL) for Mobile Edge Computing (MEC) | This algorithm captures the dynamics of the MEC environment by integrating the Dueling Double Deep Q-Network (D3QN) model with Long Short-Term Memory (LSTM) networks.

Research of using MEC in V2X communications

A platform for event managers and participants for EXCEL 2018

An Hybrid Edge Infrastructure for 5G Networks deployed on Kubernetes and enhanced by a migration controller.

Official impl. of ACM MM paper "Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds". A distributed inference model for pedestrian attribute recognition with re-ID in an MEC-enabled camera monitoring system. Jointly training of pedestrian attribute recognition and Re-ID.

Object following tracking robot

Object following tracking robot raspberry pi

5GMETA MEC Platform Instance Management API

MEC Application Migration

Reinforcement learning-based route optimization for autonomous vehicles using SUMO and MEC architecture (CPU, Raspberry Pi, FPGA).

Edge applications that follow a moving vehicle between cells, driven by 5G core session events. SUCCESS-6G.

Python script for Enade and IDD data

Cold-start-aware binary PSO for serverless task offloading in Mobile Edge Computing. Reduces mean latency by 19% and p95 by 29% vs cold-naive PSO. Training-free, 17 ms/slot. DCCN 2026.

A Multi-access Edge Computing site on Kubernetes: kubeadm cluster, Prometheus observability spanning infrastructure, apps and the 5G radio network, ETSI OSM orchestration, and a REST API to drive it all