Abstract:
The ever-growing demand for video and data services poses a significant challenge for mobile network operators. This surge is fueled by the proliferation of high-definiti...Show MoreMetadata
Abstract:
The ever-growing demand for video and data services poses a significant challenge for mobile network operators. This surge is fueled by the proliferation of high-definition applications, online gaming, and the rise of machine-type communications' entailing exceptional Quality of Experience (QoE) for users. To address these demands, Heterogeneous Networks (HetNets) have emerged as a promising solution within 5G networks. However, the coexistence of diverse small cells in multi-tier 5GHetNets introduces complex interference issues. This paper introduces a novel Machine Learning Enhanced Classification for Interference Management and Offloading (MLCIMO) scheme. It employs multi-binary classification to categorize users by interference types and levels, improving QoE for various services and enhancing resource utilization. A comprehensive performance comparison with state-of-the-art approaches was also conducted to showcase the advantages of MLCIMO in terms of Video Multimethod Assessment Fusion (VMAF), R-Factor, and RUM Speed Index (RUMSI) metrics.
Date of Conference: 09-13 June 2024
Date Added to IEEE Xplore: 20 August 2024
ISBN Information: