vrAIn: Deep Learning based Orchestration for Computing and Radio Resources in vRANs

Abstract

The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex relationship between computing and radio dynamics make vRAN resource control particularly daunting. We present vrAIn, a resource orchestrator for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and channel quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map contexts into resource control decisions. We have evaluated vrAIn experimentally, using an open-source LTE stack over different platforms, and via simulations over a production RAN. Our results show that: (i) vrAIn provides savings in computing capacity of up to 30% over CPU-agnostic methods; (ii) it improves the probability of meeting QoS targets by 25% over static policies; (iii) upon computing capacity under-provisioning, vrAIn improves throughput by 25% over state-of-the-art schemes; and (iv) it performs close to an optimal offline oracle. To our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs and the first approach to a model-free solution that does not need to assume any particular platform or context.

Understanding the Performance of Flexible Functional Split in 5G vRAN Controllers: A Markov Chain-Based Model

“…A machine-learning based solution is proposed in [42] to manage computation resources in the vRAN controller. In addition, the authors carefully analyze the computational load required by the different network functions, using a Software Defined Radio (SDR) implementation.…”

Scope

“…We are aware of only a handful of works concerning network slicing implementations for srsLTE-based cellular networks. Garcia-Aviles et al propose a multi-slice service-orchestration framework [23] and implement it on a small-scale prototype [24], while Ayala-Romero et al devise a deep learning approach for joint allocation of computational and radio resources [3]. Furthermore, D'Oro et al proposed a multi-access edge computing (MEC) framework for resource orchestration on heterogeneous network slices [21], and demonstrated optimal network slicing solutions for small-scale 5G network deployments [20].…”

Traffic-Driven Sounding Reference Signal Resource Allocation in (Beyond) 5G Networks

“…We then sort U in descending order of a u (line 19) and schedule the first UEs in the set until the available R resource units are used. This builds the schedule X and for these users we update the information in U by setting the age of estimate to 0 and the last scheduled SRS as the current frame t (lines [20][21][22][23][24].…”

“…Mobile network traffic prediction. Real-time data traffic forecast are a paramount input to emerging strategies in traffic engineering and resource management that take advantage of the increasing virtualization of mobile networks, as repeatedly demonstrated by many recent studies [22], [23], [24]. In this context, traditional models relying on information theory [25], Markovian [26] or autoregressive [27] approaches have been supplanted by deep learning architectures.…”