Machine Learning Enables Predictive Resource Recommendation for Minimal Latency Mobile Networking

Abstract

To achieve the minimal latency, proactive wireless communication has been proposed to facilitate proactive mobile networks. Due to lacking closed-loop control, random selection of radio resource units (RRUs) serves the only way to the critical radio resource allocation (RRA), which inevitably suffers collisions of simultaneous utilizing the same RRUs to result in loss of packets, particularly in the uplink. Macroscopic view on the uplink and downlink network operation cycle insightfully suggests that it is still possible to construct a delayed version of semi-closed-loop operation to predictively utilize radio resource in the uplink of proactive mobile network. A two-stage reinforcement learning mechanism to enable the recommendation of radio resource utilization from network infrastructure to mobile smart machines is proposed, which consists of the multi-armed bandit scheme for RRA and the neural network to learn historical utilization of RRUs. Simulations verify machine learning enables smart and predictive RRA with superior performance that can lead to the minimal latency of mobile networking.