On the use of Probabilistic Forecasting for Network Analysis in Open RAN

TL;DR

This paper explores the integration of probabilistic forecasting methods into Open RAN to improve resource demand estimation, demonstrating their superior accuracy over traditional single-point methods like LSTM.

Contribution

It proposes using probabilistic forecasting as a radio app within Open RAN and compares various methods, highlighting DeepAR's superior performance.

Findings

DeepAR outperforms LSTM and SN baselines in accuracy.

Probabilistic forecasting provides more reliable resource estimates.

Probabilistic methods show numerical advantages over traditional techniques.

Abstract

Unlike other single-point Artificial Intelligence (AI)-based prediction techniques, such as Long-Short Term Memory (LSTM), probabilistic forecasting techniques (e.g., DeepAR and Transformer) provide a range of possible outcomes and associated probabilities that enable decision makers to make more informed and robust decisions. At the same time, the architecture of Open RAN has emerged as a revolutionary approach for mobile networks, aiming at openness, interoperability and innovation in the ecosystem of RAN. In this paper, we propose the use of probabilistic forecasting techniques as a radio App (rApp) within the Open RAN architecture. We investigate and compare different probabilistic and single-point forecasting methods and algorithms to estimate the utilization and resource demands of Physical Resource Blocks (PRBs) of cellular base stations. Through our evaluations, we demonstrate the numerical advantages of probabilistic forecasting techniques over traditional single-point forecasting methods and show that they are capable of providing more accurate and reliable estimates. In particular, DeepAR clearly outperforms single-point forecasting techniques such as LSTM and Seasonal-Naive (SN) baselines and other probabilistic forecasting techniques such as Simple-Feed-Forward (SFF) and Transformer neural networks.