vrAIn: Deep Learning based Orchestration for Computing and Radio Resources in vRANs
- 8 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1
Abstract
The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic 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.Keywords
Funding Information
- AEI FEDER (EC2016-76465-C2-1-R)
- European Commission (856709, 856950)
- Science Foundation Ireland (17/CDA/4760)
This publication has 39 references indexed in Scilit:
- Are Heterogeneous Cloud-Based Radio Access Networks Cost Effective?IEEE Journal on Selected Areas in Communications, 2015
- Human-level control through deep reinforcement learningNature, 2015
- QoS-Aware Power-Efficient Scheduler for LTE UplinkIEEE Transactions on Mobile Computing, 2014
- Max–Min Energy-Efficient Power Allocation in Interference-Limited Wireless NetworksIEEE Transactions on Vehicular Technology, 2014
- Cloud RAN for Mobile Networks—A Technology OverviewIEEE Communications Surveys & Tutorials, 2014
- Joint Resource Allocation for Max-Min Throughput in Multicell NetworksIEEE Transactions on Vehicular Technology, 2014
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- Principal Component Analysis on Spatial Data: An OverviewAnnals of the American Association of Geographers, 2013
- Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks, 1998
- Q-learningMachine Learning, 1992