PROJECT TITLE :

Learning-Based Uplink Interference Management in 4G LTE Cellular Systems

ABSTRACT:

LTE's uplink (UL) efficiency critically depends on how the interference across completely different cells is controlled. The unique characteristics of LTE's modulation and UL resource assignment poses considerable challenges in achieving this goal as a result of most LTE deployments have one:one frequency reuse, and the uplink interference can vary considerably across successive time-slots. In this paper, we tend to propose LeAP, a measurement knowledge-driven machine learning paradigm for power management to manage uplink interference in LTE. The information-driven approach has the inherent advantage that the solution adapts primarily based on network traffic, propagation, and network topology, which is increasingly heterogeneous with multiple cell-overlays. LeAP system style consists of the subsequent elements: one) design of user equipment (UE) measurement statistics that are succinct, however expressive enough to capture the network dynamics, and 2) design of 2 learning-based mostly algorithms that use the reported measurements to line the power management parameters and optimize the network performance. LeAP is standards-compliant and will be implemented in a very centralized self-organized networking (SON) server resource (cloud). We tend to perform extensive evaluations using radio network plans from a real LTE network operational in a major metro space within the US. Our results show that, compared to existing approaches, LeAP provides 4.nine× gain within the 20th percentile of user data rate, three.25× gain in median knowledge rate.