ML Approach for Power Consumption Prediction in Virtualized Base Stations

TL;DR

This paper presents a neural network-based model for predicting power consumption in virtualized base stations within O-RAN, offering a flexible alternative to traditional domain-knowledge methods.

Contribution

It introduces a black-box neural network approach for power prediction that performs comparably to domain-based solutions without requiring prior system knowledge.

Findings

Neural network model achieves similar accuracy to hand-crafted solutions.

The approach offers greater flexibility in unknown or complex system scenarios.

Model can be trained using data collected via O-RAN infrastructure.

Abstract

The flexibility introduced with the Open Radio Access Network (O-RAN) architecture allows us to think beyond static configurations in all parts of the network. This paper addresses the issue related to predicting the power consumption of different radio schedulers, and the potential offered by O-RAN to collect data, train models, and deploy policies to control the power consumption. We propose a black-box (Neural Network) model to learn the power consumption function. We compare our approach with a known hand-crafted solution based on domain knowledge. Our solution reaches similar performance without any previous knowledge of the application and provides more flexibility in scenarios where the system behavior is not well understood or the domain knowledge is not available.