Adaptive Range-based Anomaly Detection in Drone-assisted Cellular Networks

Abstract

Stimulated by the emerging Internet of Things (IoT) applications and their massive generated data, the cellular providers are introducing various IoT functionalities into their networks architecture. They should integrate intelligent and autonomous mechanisms that are able to detect sudden and anomalous behavior issues. In this paper, we present an adaptive anomaly detection approach in cellular networks consisting of two parts: the detection of overloaded base-stations using machine learning algorithm (LSTM-Long Short-Term Memory) and the deployment of drones as mobile base-stations that support and back up the overloaded cells. The proposed approach is validated using real dataset extracted from the CDR of Milan combined with semi-synthetic eHealth data. Initially, The LSTM algorithm analyzes the impact of eHealth applications on cellular networks and identifies cells with peak demands. Then, drones are deployed to collect the requested data from these cells. The obtained results show that the use of drones improves the quality of service and provides a better network performance.

Models for Real/Non-Realtime Traffic QoS in UAV Assisted Cellular Networks

“…Another two papers [3] and [6] targeted the same problem statement of proposing the use of drones to overcome unplanned events in the cellular network. The first work suggested using long-term memory (LSTM) to detect unplanned events and to satisfy the additional BW required in cells.…”

“…while others propose an optimal model for the position of the drones. These contributions didn't mention the use of drones to overcome the rapid increase of BW demands in the specific cells during unplanned events except the work of [4], [3], and [6]. But these mentioned works didn't take into consideration the different traffic types based on the time.…”

“…UAVs (Drones) can be exploited for communications, and can serve as a flying base station (BS) to temporarily cover a specific location [1] and help in offloading traffic. In addition, it can be used to increase the cell bandwidth (BW) when there is high traffic due to an event (anomaly) [2], [3].…”