Abstract
The deployment of mobile-Small cells (mScs) is widely adopted to
intensify the quality-of-service (QoS) in high mobility vehicles.
However, the rapidly varying interference patterns among densely
deployed mScs make the resource allocation (RA) highly challenging. In
such scenarios, RA problem needs to be solved nearly in real-time, which
can be considered as drawback for most existing RA algorithms. To
overcome this constraint and solve the RA problem efficiently, we use
deep learning (DL) in this work due to its ability to leverage the
historical data in RA problem and to deal with computationally expensive
tasks offline. More specifically, this paper considers the RA problem in
vehicular environment comprising of city buses, where DL is explored for
optimization of network performance. Simulation results reveal that RA
in a network using Long Short-Term Memory (LSTM) algorithm outperforms
other machine learning (ML) and DL-based RA mechanisms. Moreover, RA
using LSTM provides less accurate results as compared to existing Time
Interval Dependent Interference Graph (TIDIG)-based, and Threshold
Percentage Dependent Interference Graph (TPDIG)-based RA but shows
improved results when compared to RA using Global Positioning System
Dependent Interference Graph (GPSDIG). However, the proposed scheme is
computationally less expensive in comparison with TIDIG and TPDIG-based
algorithms.