Skip to content
View Narvalaina's full-sized avatar
  • Alicante, Spain

Block or report Narvalaina

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Narvalaina/README.md

Fernando Tomás Gámez Cartagena

Telecommunications Engineer focused on communications systems, satellite communications, RF/microwave, networking/SDN, signal processing, and systems engineering.

My technical work combines reproducible communications and networking systems with data-driven modelling for traffic analysis and prediction.

Engineering focus

  • Communications systems and satellite communications
  • RF/microwave and digital communications
  • IP networking, SDN/OpenFlow, Mininet, Open vSwitch and OpenDaylight
  • Signal processing and data-driven traffic analysis
  • Systems engineering, integration, verification and validation

Featured projects

IP Traffic Forecasting with Machine Learning

Research repository developed from my master's thesis at Universidad Miguel Hernández, defended with a grade of 10/10.

The project compares statistical, machine-learning and deep-learning approaches for multihorizon IP traffic forecasting on UGR'16, using a temporally separated March → April → June protocol with external evaluation, cross-family analysis, residual diagnostics, and reproducibility documentation.

Model families include ARIMA, VAR, Ridge, tree ensembles, RNN, LSTM, GRU, and a lightweight Transformer. The final evidence supports no universal winner: performance depends on forecast horizon, metric, temporal regime, training history, stability, and computational cost.

Explore the repository →

SDN Fat-Tree Testbed

Reproducible SDN testbed developed from my bachelor's thesis at Universidad Miguel Hernández, defended with a grade of 10/10.

The project covers incremental validation from basic topologies to Leaf-Spine and a Fat-Tree k=4, deterministic OpenDaylight RESTCONF forwarding, bounded OpenFlow select-group ECMP experiments, reproducibility checks, and public engineering evidence.

Explore the repository →

Current direction

Communications systems, satellite communications, RF/microwave, networking, signal processing, and systems engineering, with a particular focus on aerospace and NewSpace applications.

Pinned Loading

  1. sdn-fattree-testbed sdn-fattree-testbed Public

    Reproducible SDN testbed for Leaf-Spine and k-ary Fat-Tree experiments with Mininet, Open vSwitch and OpenDaylight.

    Python

  2. ip-traffic-forecasting-ml ip-traffic-forecasting-ml Public

    IP traffic forecasting across statistical, machine-learning and deep-learning models — Master's Thesis research repository.

    Python