A Statistical Learning Approach to Ultra-Reliable Low Latency Communication

Abstract

Mission-critical applications require Ultra-Reliable Low Latency (URLLC) wireless connections, where the packet error rate (PER) goes down to 10 −9 . Fulfillment of the bold reliability figures becomes meaningful only if it can be related to a statistical model in which the URLLC system operates. However, this model is generally not known and needs to be learned by sampling the wireless environment. In this paper we treat this fundamental problem in the simplest possible communicationtheoretic setting: selecting a transmission rate over a dynamic wireless channel in order to guarantee high transmission reliability. We introduce a novel statistical framework for design and assessment of URLLC systems, consisting of three key components: (i) channel model selection; (ii) learning the model using training; (3) selecting the transmission rate to satisfy the required reliability. As it is insufficient to specify the URLLC requirements only through PER, two types of statistical constraints are introduced, Averaged Reliability (AR) and Probably Correct Reliability (PCR). The analysis and the evaluations show that adequate model selection and learning are indispensable for designing consistent physical layer that asymptotically behaves as if the channel was known perfectly, while maintaining the reliability requirements in URLLC systems.

Wireless Access in Ultra-Reliable Low-Latency Communication (URLLC)

“…However, if the true channel differs even slightly from the assumed model (e.g. a small specular component is also present), the rate is not longer consistent and both the AR and PCR constraints will be violated, see [47] for in-depth discussions. This can be viewed as a general pitfall of parametric channel models; while they provide fast convergence, they are prone to significant bias which lead to inconsistent rate and severe reliability violations.…”

“…As an alternative, one can consider non-parametric channel modeling approaches. They indeed are guaranteed to give consistent rates under very mild channel restrictions but they require extensive training; in fact, the number of channel samples necessary to obtain non-negative transmission rate grows as [47] n ∼ 1 .…”

“…Finally, [47] suggests to use power law approximations of the channel tail as third alternative as they provide "the best of the two worlds"; even though they do not guarantee rate consistency due to approximation error, they are significantly less biased than poor parametric models and they require reasonable training samples lengths.…”

A Very Brief Introduction to Machine Learning With Applications to Communication Systems

“…First, the phenomenon or function being learned should not change too rapidly over time. For example, designing a channel decoder based on samples obtained from a limited number of realizations of a given propagation channel requires the channel is stationary over a sufficiently long period of time (see [28]).…”

Ultra-Reliable and Low-Latency Vehicular Communication: An Active Learning Approach

“…In [3] and [4], the network dynamics are assumed to be known and in [5], they are estimated in a centralized manner without any consideration of future AoI. Yet, in a URLLC setting [6], [7], reliably learning and estimating the network dynamics with minimum communication overhead is desirable. Due to the highly dynamic nature of vehicular networks, gaining knowledge a priori about the network dynamics is challenging.…”