Alert button
Picture for Supratim Deb

Supratim Deb

Alert button

Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks

Aug 23, 2018
Michele Polese, Rittwik Jana, Velin Kounev, Ke Zhang, Supratim Deb, Michele Zorzi

Figure 1 for Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
Figure 2 for Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
Figure 3 for Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
Figure 4 for Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks

The fifth generation of cellular networks (5G) will rely on edge cloud deployments to satisfy the ultra-low latency demand of future applications. In this paper, we argue that an edge-based deployment can also be used as an enabler of advanced Machine Learning (ML) applications in cellular networks, thanks to the balance it strikes between a completely distributed and a centralized approach. First, we will present an edge-controller-based architecture for cellular networks. Second, by using real data from hundreds of base stations of a major U.S. national operator, we will provide insights on how to dynamically cluster the base stations under the domain of each controller. Third, we will describe how these controllers can be used to run ML algorithms to predict the number of users, and a use case in which these predictions are used by a higher-layer application to route vehicular traffic according to network Key Performance Indicators (KPIs). We show that prediction accuracy improves when based on machine learning algorithms that exploit the controllers' view with respect to when it is based only on the local data of each single base station.

* 30 pages, 10 figures, 3 tables. Submitted to IEEE JSAC Special Issue on Special Issue on Artificial Intelligence and Machine Learning for Networking and Communications 
Viaarxiv icon

Learning Latent Events from Network Message Logs: A Decomposition Based Approach

Apr 10, 2018
Siddhartha Satpathi, Supratim Deb, R Srikant, He Yan

Figure 1 for Learning Latent Events from Network Message Logs: A Decomposition Based Approach

In this communication, we describe a novel technique for event mining using a decomposition based approach that combines non-parametric change-point detection with LDA. We prove theoretical guarantees about sample-complexity and consistency of the approach. In a companion paper, we will perform a thorough evaluation of our approach with detailed experiments.

Viaarxiv icon