GitHub Artifacts

CloudRIC is a system that meets specific reliability targets in 5G FEC processing while sharing pools of heterogeneous processors among DUs, which leads to more cost- and energy-efficient vRANs. The details of the solution are presented in https://doi.org/10.1145/3636534.3649381. As described therein, CloudRIC exploits data-driven models of Logical Processing Units. This repository includes the LPU models of an Intel Xeon Gold 6240R CPU and of an NVIDIA GPU V100 and the tools to replicate the results shown in Figs. 16 and 17 of https://doi.org/10.1145/3636534.3649381

https://github.com/h2020daemon/CloudRIC

February, 2024

kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices

Partner: IMDEA

Code implemented in the paper: "kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices", published in MobiHoc 2023, the 24th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing

https://github.com/h2020daemon/kansaas

September, 2023

Open source SDR 4G software suite from Software Radio Systems (SRS)

Partner: SRS

The srsRAN suite includes:

srsUE - a full-stack SDR 4G UE application with prototype 5G features
srsENB - a full-stack SDR 4G eNodeB application
srsEPC - a light-weight 4G core network implementation with MME, HSS and S/P-GW

https://github.com/h2020daemon/srsRAN_4G

April, 2023

Kubernetes version of Open5Gs

Partner: UC3M

Design and Validation of an Open Source Cloud Native Mobile Network

The repository contains the code of the paper "Design and Validation of an Open Source Cloud Native Mobile Network" by N. Apostolakis, M. Gramaglia, P. Serrano. Please cite the paper if you plan to use it in your publication.

https://github.com/h2020daemon/k8s-open5gs

February, 2023

AutoManager: a Meta-Learning Model for Network Management from Intertwined Forecasts

Partner: IMDEA

AutoManager: a Meta-Learning Model for Network Management from Intertwined Forecasts

https://github.com/h2020daemon/AutoManager

January, 2023

Flowrest: in-switch flow-level classification with random forests

Partner: IMDEA

This repository contains the public version of the code for our work Flowrest which will appear in the Proceedings of IEEE INFOCOM 2023, 17-20 May 2023, New York Area, USA.

https://github.com/h2020daemon/Flowrest

January, 2023

Nemo2 is a tool to Model and Transform by Bit-Blasting Numerical Feature Models into different Propositional Formulas and Universal Variability Language (UVL) Models

Partner: UMA

The current version of Nemo transforms Numerical Feature Models (NFMs) into an optimized Tseitin’s Conjunctive Normal Form (CNF) propositional formula by means of Bit-Blasting. Nemo is a cross-platform tool that have been developed in Python.

Nemo2 outputs support three formats: a) a UVL model, b) a propositional formula, and c) a Tseitin’s Conjunctive Normal Form (CNF) propositional formula. Besides the transformed model, we make use of comment lines to identify each original feature name and domain (i.e., boolean or numerical) with their respectives bit-blasted features.

https://github.com/h2020daemon/Nemo2_tool

License:

https://www.safecreative.org/work/2303303911430-nemo

January, 2023

Henna: Hierarchical Machine Learning Inference in Programmable Switches

Partner: IMDEA

This repository contains the public version of the code for our work Henna, presented at the 1st ACM CoNEXT Workshop on Native Network Intelligence (NativeNI '22), 9 December 2022, Roma, Italy.

https://github.com/h2020daemon/Henna

December, 2022

Nemo is a tool to transform Numerical Feature Models into a CNF DIMACS file by means of Bit-Blasting

Partner: UMA

https://github.com/h2020daemon/Nemo_tool

License:

https://www.safecreative.org/work/2303303911430-nemo

December, 2022

TES-RNN

Partner: IMDEA

TES-RNN Model (GPU implementation) used in "Forecasting for Network Management with Joint Statistical Modelling and Machine Learning" paper published in 2022 IEEE 23rd International Symposium on "A World of Wireless, Mobile and Multimedia Networks (WoWMoM)"

https://github.com/h2020daemon/wowmom22_tes-rnn

April, 2022

Loss Learning Predictor for regression problems

Partner: IMDEA

Code of Flowrest: used datasets: D7, D12, D13, D14, Evaluation E8 and Testbed : T12

https://github.com/h2020daemon/LossLeaP

January, 2022

Open source SDR LTE software suite from Software Radio Systems (SRS)

Partner: UC3M

It includes:

srsUE - a complete SDR LTE UE application featuring all layers from PHY to IP
srsENB - a complete SDR LTE eNodeB application
srsEPC - a light-weight LTE core network implementation with MME, HSS and S/P-GW
a highly modular set of common libraries for PHY, MAC, RLC, PDCP, RRC, NAS, S1AP and GW layers.

https://github.com/h2020daemon/srsLTE

November, 2021

Energy-driven joint vRAN & edge service orchestration (D4.2, Section 2.4)

Partner: NEC

This code implements the constrained contextual Bayesian optimization algorithm used in the paper:

Jose A. Ayala-Romero, A. Garcia-Saavedra, X. Costa-Perez, G. Iosifidis (2021). EdgeBOL: Automating Energy-savings for Mobile Edge AI. ACM CoNEXT 2021.

https://github.com/h2020daemon/constrained_bayes_opt

November, 2021

Energy-driven vRAN orchestration (D4.2, Section 2.3) Bayesian online learning

Partner: NEC

This code implements the contextual Bayesian optimization algorithm used in the paper: Jose A. Ayala-Romero, A. Garcia-Saavedra, X. Costa-Perez, G. Iosifidis (2021). Bayesian Online Learning for Energy-Aware Resource Orchestration in Virtualized RANs. IEEE INFOCOM 2021.

https://github.com/h2020daemon/contextual_bayesian_optimization

January, 2021

Data-sets:

Experimental characterization of NEC Reconfigurable Intelligent Surface

Partner: NEC

Here we provide the dataset containing the power measurements carried out in the anechoic chamber of TU Darmstadt.

The test was performed under the following conditions:

TX at 1.1m away from RIS with 33° elevation angle and θ_t = [20°,90°]
RX at 6.3m away from RIS with -3° elevation angle and θ_t = [90°]
Horn antennas gain = 13.5 dBi
OFDM QPSK-modulated symbols with 5 MHz of bandwidth, numerology that meets LTE requirements.
TX power per subcarrier = -30 dBm
Reference signal received power (RSRP) sampling at RX
Noise floor = -90dBm

For more details, please refer to sec. 5 of our paper.

In the CSV file, the pair (θ_n, Φ_n) defines the RIS main beam location: θ_n for the azimuth and Φ_n for the elevation. Instead, θ_r indicates the angle for the radiation pattern varying with a step of 3° on the azimuth.

In the RIS_beamforming file, data regarding how the RIS is able to generate beamforming by changing the number of active antenna elements.

https://github.com/h2020daemon/RIS-Power-Measurements-Dataset

February, 2024

DATA: Latency and energy consumption characterization of a CPU and a GPU LDPC decoder

Partner: NEC, IMDEA, i2CAT, UC3M

https://github.com/h2020daemon/CloudRic-Artifacts

February, 2024

DATA: HADES: An NFV solution for energy-efficient placement and resource allocation in heterogeneous infrastructures

Ángel Cañete; Mercedes Amor; Lidia Fuentes

Members of: ITIS Software | Universidad de Málaga

This dataset contains the following:

1 CSV file with execution time results of the iTAREA module for (60) different problem sizes and (3) execution environments.
1 CSV file with energy consumption results of HADES deployments and other 5 assignment policies: First-fit, Random-fit, Fastest-fit, Best-fit, and kube-scheduler (the Kubernetes’ assignment policy).

https://doi.org/10.5281/zenodo.7712024

September 8, 2022

DATA: Quality-aware Analysis and Optimisation of Virtual Network Functions

Daniel-Jesus Munoz; Monica Pinto; Lidia Fuentes

Members of: ITIS Software | Universidad de Málaga

This data-set contains:

The 5 SPL categories in CQL alongside the 11 tested operations.
The 5 SPL Clafer models.
The 5 SPL XMLs (for the AAFM Python Framework).
The 5 SPL XMLs (for SATIBEA).
The previous models are enriched with quality attributes measurements at feature and configuration levels.
A Microsoft Excel file with the scalability results obtained.

https://github.com/h2020daemon/SPLC22

September 8, 2022

Traffic Classification directly on spectrum data

M. Camelo, P. Soto and S. Latré

Members of: IMEC

This repository contains the code the can be used to reproduce the results in the paper: "A General Approach for Traffic Classification in Wireless Networks using Deep Learning".

https://github.com/h2020daemon/tc_spectrum

September 8, 2022

Energy edge AI dataset

Ayala-Romero, Jose A and Garcia-Saavedra, Andres and Costa-Perez, Xavier and Iosifidis, George

Members of: NEC

Dataset of measurements of performance and power consumption of an AI service at the network edge. The experimental setup is comprised of a 3GPP R10-compliant LTE base station (BS), a user equipment (UE) generating service requests via the BS to a well-known object recognition service, and an off-the-shelf server with an NVIDIA GPU running the service. Each request consists of an image with a variable number of objects from the COCO dataset. The images are sent to the service via the uplink channel of the LTE interface, and the service returns bounding boxes and a classification label of the identified objects to the user via the downlink channel of the LTE interface.

https://github.com/h2020daemon/SPLC22

September 8, 2022

Energy consumption, execution time and fail requests rate of a proactive energy-aware auto-scaling solution for edge-based infrastructures applied to real-world workload

Cañete, Ángel; Djemame, Karim; Amor, Mercedes; Fuentes, Lidia; Aljulayfi, Abdullah.

Members of: ITIS Software | Universidad de Málaga

Spreadsheet of the results obtained with our horizontal auto-scaling proposal presented in "A proactive energy-aware auto-scaling solution for edge-based infrastructures".

https://doi.org/10.5281/zenodo.7248106

February 24, 2022

Smart Analyser of Variability Requirements of Unknown Spaces (SAVRUS) Dataset of a study with 5 real-world large numerical variability models

Daniel-Jesus Munoz; Monica Pinto; Lidia Fuentes

Members of: ITIS Software | Universidad de Málaga

The dataset zip file contains:

5 numerical variability models in Clafer format (.txt) for each software product line.
5 CSV files with the respective quality attribute measurements
An .xlsx file containing SAVRUS scalability results divided in different tabs.

https://doi.org/10.5281/zenodo.6251045

Licenses:

https://www.safecreative.org/work/2303303911454-savrus

https://www.safecreative.org/work/2303303909024-hadas

February 24, 2022

Energy-driven joint vRAN & edge service orchestration (D4.2, Section 2.4)

Partner: NEC

We provide two files. In 'ai_edge_dataset.csv', each value is the average of 150 images from COCO dataset. Moreover, we provide the per-image values in 'ai_edge_dataset_all.csv'. The details of the experiments and the software and hardware used can be found in the paper:

Jose A. Ayala-Romero, A. Garcia-Saavedra, X. Costa-Perez, G. Iosifidis (2021). EdgeBOL: Automating Energy-savings for Mobile Edge AI. ACM CoNEXT 2021.

https://github.com/h2020daemon/energy_edge_AI_dataset

November, 2021

IDLAB-UA Dataset for Traffic Classification using Spectrum

Camelo, Miguel

Members of: IMEC

This dataset contains IQ values of physical layer (L1) packets associated with WLAN transmission and the set of labels that associated each of the packets to properties/features at different radio stack layer (from L1 to L7)

https://doi.org/10.5281/zenodo.5208201

August 16, 2021

AutoML for Video Analytics with Edge Computing

Galanopoulos, Apostolos; Ayala-Romero, Jose; Leith, Douglas; Iosifidis, George

Members of: TU Delft

Latency and confidence measurements obtained from an edge-assisted object recognition system.

https://doi.org/10.5281/zenodo.6259141

June 16, 2021

Bayesian Online Learning for Energy-Aware Resource Orchestration in Virtualized RANs

Ayala-Romero, Jose; Garcia-Saavedra, Andres; Costa-Perez, Xavier; Iosifidis, George

Members of: TU Delft

Dataset providing a set of measurement of performance and power consumpetion of a virtualized Base Station (srseNB)

https://doi.org/10.5281/zenodo.6258750

June 16, 2021