Robust Cell-Load Learning with a Small Sample Set

TL;DR

This paper introduces a robust learning framework for cell-load prediction in radio access networks that effectively utilizes prior knowledge and small training sets to improve accuracy and robustness.

Contribution

The paper develops a novel learning approach that incorporates prior knowledge and proves properties of the feasible rate region to enhance cell-load prediction with limited data.

Findings

Outperforms standard methods in small sample scenarios

Guarantees minimum worst-case approximation error

Demonstrates robustness and accuracy improvements in NS3 simulations

Abstract

Learning of the cell-load in radio access networks (RANs) has to be performed within a short time period. Therefore, we propose a learning framework that is robust against uncertainties resulting from the need for learning based on a relatively small training sample set. To this end, we incorporate prior knowledge about the cell-load in the learning framework. For example, an inherent property of the cell-load is that it is monotonic in downlink (data) rates. To obtain additional prior knowledge we first study the feasible rate region, i.e., the set of all vectors of user rates that can be supported by the network. We prove that the feasible rate region is compact. Moreover, we show the existence of a Lipschitz function that maps feasible rate vectors to cell-load vectors. With these results in hand, we present a learning technique that guarantees a minimum approximation error in the worst-case scenario by using prior knowledge and a small training sample set. Simulations in the network simulator NS3 demonstrate that the proposed method exhibits better robustness and accuracy than standard multivariate learning techniques, especially for small training sample sets.