First, we collected the 5G network slicing dataset, which involves the attributes associated with various network devices like "user device type, duration, packet loss ratio, packet delay budget, bandwidth, delay rate, speed, jitter, and modulation type." Next, we performed the OWFE, in which...
This study involved the creation of datasets to enable simulations for scenarios with URLLC and mMTC slicing optimizations. Each dataset comprises 100 timesteps, that accommodate a flexible configuration of frequencies and devices per frequency to capture various operational scenarios. The datasets consist...
If you use this dataset and code or any herein modified part of it in any publication, please cite these papers: A. Thantharate, R. Paropkari, V. Walunj and C. Beard, "DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks," 2019 IEEE ...
To validate the effectiveness, we collect an extensive network port traffic dataset (NPT) from the intelligent metropolitan network delivering 5G services of China Unicom and compare the proposed model with numerous current arts over multiple applications. We make two distinct research contributions to ...
2.2.8Network slicing 5G network slicing [16] is a novel architectural concept to enable the diverse set of use cases currently envisioned for 5G. Virtual end-to-end-networks or “slices” are created for each 5G service, which may require a different air interface per slice tailored to a ...
For 5G, this concept will be a realization of the Network Slicing concept promised in advanced versions of the 5G network technology. Support for private LTE and 5G allows factories to limit opex spend (i.e., connectivity fees payable to operators), geofence sensitive data, and scale up ...
Current wireless network learning approaches have focused on traditional machine learning (ML) algorithms, which centralize the training data and perform sequential model learning over a large data set. However, performing training on a large dataset is inefficient; it is time-consuming and not energy...
Hence, test of datasets in diverse situations needs to give more attention to this aspect for dataset training and feature selection. Sensors and humans, for example, create data for IoT networks in smart homes. However, a common or central server must contain all the data utilized in this ...
Our contributions address this gap by generating a network slicing dataset and developing a GNN model for predicting the KPIs of simulated network slices. Table 1. Comparison GNNetSlice and other contributions focusing on GNN and network slicing. ContributionDeep learning modelArchitectureGround truth...
It is to be noted that the 5G mobile network dataset employed in our model is obtained by a commercial operator in Armenia. (ii) Our previous work used the ILP technique to solve solely the VxF (not SFC) placement problem with specific latency demands as requested by UEs. However, the ...