Assign Hysteresis Parameter For Ericsson BTS Power Saving Algorithm Using Unsupervised Learning

TL;DR

This paper presents an unsupervised learning model to optimize the hysteresis parameter in Ericsson BTS power saving algorithms, reducing active TRX by 20.9% to save power amid electricity shortages.

Contribution

It introduces a novel unsupervised clustering approach to select optimal hysteresis parameters for GSM BTS power saving, improving energy efficiency.

Findings

Reduced number of active TRX by 20.9%.

Optimized power consumption in telecommunication equipment.

Enhanced parameter selection process for BTS power saving.

Abstract

Gaza Strip suffers from a chronic electricity deficit that affects all industries including the telecommunication field, so there is a need to optimize and reduce power consumption of the telecommunication equipment. In this paper we propose a new model that helps GSM radio frequency engineers to choose the optimal value of hysteresis parameter for Ericsson BTS power saving algorithm which aims to switch OFF unused frequency channels, our model is based on unsupervised machine learning clustering K-means algorithm. By using our model with BTS power saving algorithm we reduce number of active TRX by 20.9%.