Abstract | ||
---|---|---|
Current reactive mobility management in cellular networks becomes a bottleneck for ultra-low latency 5G services and severely degrades the QoS. To satisfy the ultra-low latency requirement of 5G services, proactive mobility management is essential where next PoA of the user is predicted with minimal error. Recent studies have used different deep learning algorithms for this purpose, but their results are unacceptable in real networks due to low accuracy. This paper exploits the distributional learning capability of Generative Adversarial Network (GAN) to propose MoGAN for the prediction of user's next PoA. The generator in MoGAN uses Gated Recurrent Unit to learn the distribution of time-series data and generates the next PoA. Meanwhile, the discriminator evaluates the generated output against the real data to determine its correctness. The model is trained in adversary mode by using the output from the discriminator. The dataset utilized in training and evaluation is collected from one of the university campuses, and the results show 96.33% of prediction accuracy, which is 5% higher than the previous study. Furthermore, MoGAN is more robust under limited data conditions, as it achieves above 90% accuracy with only 50% of the dataset. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICNP49622.2020.9259368 | 2020 IEEE 28th International Conference on Network Protocols (ICNP) |
Keywords | DocType | ISSN |
Generative Adversarial Network,Gated Recurrent Unit,Deep learning,Mobility management,Prediction | Conference | 1092-1648 |
ISBN | Citations | PageRank |
978-1-7281-6993-4 | 0 | 0.34 |
References | Authors | |
9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Boyun Jang | 1 | 0 | 0.34 |
Syed M. Raza | 2 | 18 | 8.68 |
Moonseong Kim | 3 | 143 | 39.75 |
Hyunseung Choo | 4 | 1364 | 195.25 |