5G and the next generation networks are expected to support diverse quality of service (QoS) requirements while ensuring network energy efficiency in the face of increasing mobile data traffic. However, wireless networks are resource-constrained, and ensuring QoS guarantees and maintaining energy efficiency is a challenging task. Rapid fluctuation of signal quality due to the mobility of the user equipment (UE) makes the task more complicated. Nevertheless, user mobility is not entirely random (e.g., UE with vehicle speed traveling along a highway) and results in channel gain that significantly varies with time. Since mobility factors (speed, location, direction of movement) and received signal strength are correlated, user mobility can be exploited to enhance resource allocation decisions and thus improve both UE QoS and network energy efficiency. In this paper, we propose a deep reinforcement learning (DRL)-based mobility and QoS-aware downlink scheduling algorithm that takes advantage of user mobility information to minimize network energy consumption. Using reference signal received power (RSRP) measurement reports, the proposed algorithm incorporates mobility awareness into the scheduling rule to decide whether to serve UE in the current time slot or future slots, within the packet delay budget. By jointly considering packet remaining due-time and mobility information, the algorithm schedules transmissions of packets at lower power, improving energy efficiency while meeting QoS requirements. Simulation results demonstrate that the proposed approach reduces energy consumption by 18.2% and improves QoS satisfaction compared to existing methods.

In this work, we propose a distributed learning framework that classifies users' transportation modes by leveraging heterogeneous networks (HetNets) architecture and employing a federated learning (FL) algorithm. The ultra-densification of small cells and the dynamic mobility of users impact performance by triggering unnecessary handovers. Therefore, information on user mobility allows the network to perform handover management more intelligently and efficiently. The proposed machine learning framework adopts distributed learning using a federated learning algorithm to detect transportation modes, including driving a car, riding a bicycle, walking, and running. In the proposed framework, local models are trained at small cells using user history information inherently distributed on the network side. A macro cell aggregates the local models to get a global model for classifying the transportation modes of users. Training the local models by small cells over user history information addresses critical FL issues, such as non-independent and identically distributed data and system heterogeneity. Simulation results demonstrate that the proposed framework achieves an accuracy of 98.85% in classifying transportation modes, utilizing input features extracted from user history information.