# Optimal and Fast Real-time Resources Slicing with Deep Dueling Neural Networks

## TL;DR

This paper introduces a deep dueling neural network-based framework for real-time network resource slicing, significantly improving speed and long-term return by effectively handling demand uncertainty and resource optimization.

## Contribution

It develops a novel deep learning approach for fast, optimal resource slicing in networks, outperforming traditional Q-learning in convergence speed and efficiency.

## Key findings

- Up to 40% higher long-term average return.
- Few thousand times faster than existing methods.
- Effective handling of uncertain demand and multiple resources.

## Abstract

Effective network slicing requires an infrastructure/network provider to deal with the uncertain demand and real-time dynamics of network resource requests. Another challenge is the combinatorial optimization of numerous resources, e.g., radio, computing, and storage. This article develops an optimal and fast real-time resource slicing framework that maximizes the long-term return of the network provider while taking into account the uncertainty of resource demand from tenants. Specifically, we first propose a novel system model which enables the network provider to effectively slice various types of resources to different classes of users under separate virtual slices. We then capture the real-time arrival of slice requests by a semi-Markov decision process. To obtain the optimal resource allocation policy under the dynamics of slicing requests, e.g., uncertain service time and resource demands, a Q-learning algorithm is often adopted in the literature. However, such an algorithm is notorious for its slow convergence, especially for problems with large state/action spaces. This makes Q-learning practically inapplicable to our case in which multiple resources are simultaneously optimized. To tackle it, we propose a novel network slicing approach with an advanced deep learning architecture, called deep dueling that attains the optimal average reward much faster than the conventional Q-learning algorithm. This property is especially desirable to cope with real-time resource requests and the dynamic demands of users. Extensive simulations show that the proposed framework yields up to 40% higher long-term average return while being few thousand times faster, compared with state of the art network slicing approaches.