Next-generation wireless systems, already widely deployed, are expected to become even more prevalent in the future, representing challenges in both environmental and economic terms. This paper focuses on improving the energy efficiency of intelligent and programmable Open Radio Access Network (RAN) systems through the near-real-time dynamic activation and deactivation of Base Station (BS) Radio Frequency (RF) frontends using Deep Reinforcement Learning (DRL) algorithms, i.e., Proximal Policy Optimization (PPO) and Deep Q-Network (DQN). These algorithms run on the RAN Intelligent Controllers (RICs), part of the Open RAN architecture, and are designed to make optimal network-level decisions based on historical data without compromising stability and performance. We leverage a rich set of Key Performance Measurements (KPMs), serving as state for the DRL, to create a comprehensive representation of the RAN, alongside a set of actions that correspond to some control exercised on the RF frontend. We extend ns-O-RAN, an open-source, realistic simulator for 5G and Open RAN built on ns-3, to conduct an extensive data collection campaign. This enables us to train the agents offline with over 300,000 data points and subsequently evaluate the performance of the trained models. Results show that DRL agents improve energy efficiency by adapting to network conditions while minimally impacting the user experience. Additionally, we explore the trade-off between throughput and energy consumption offered by different DRL agent designs.

5G and beyond mobile networks will support heterogeneous use cases at an unprecedented scale, thus demanding automated control and optimization of network functionalities customized to the needs of individual users. Such fine-grained control of the Radio Access Network (RAN) is not possible with the current cellular architecture. To fill this gap, the Open RAN paradigm and its specification introduce an “open” architecture with abstractions that enable closed-loop control and provide data-driven, and intelligent optimization of the RAN at the user-level. This is obtained through custom RAN control applications (i.e., xApps) deployed on near-real-time RAN Intelligent Controller (near-RT RIC) at the edge of the network. Despite these premises, as of today the research community lacks a sandbox to build data-driven xApps, and create large-scale datasets for effective Artificial Intelligence (AI) training. In this paper, we address this by introducingns-O-RAN, a software framework that integrates a real-world, production-grade near-RT RIC with a 3GPP-based simulated environment on ns-3, enabling at the same time the development of xApps, automated large-scale data collection and testing of Deep Reinforcement Learning (DRL)-driven control policies for the optimization at the user-level. In addition, we propose the first user-specific O-RAN Traffic Steering (TS) intelligent handover framework. It uses Random Ensemble Mixture (REM), a Conservative$Q$-learning (CQL) algorithm, combined with a state-of-the-art Convolutional Neural Network (CNN) architecture, to optimally assign a serving base station to each user in the network. Our TS xApp, trained with more than 40 million data points collected by ns-O-RAN, runs on the near-RT RIC and controls the ns-O-RAN base stations. We evaluate the performance on a large-scale deployment with up to 126 users with 8 base stations, showing that the xApp-based handover improves throughput and spectral efficiency by an average of 50% over traditional handover heuristics, with less mobility overhead.

Augmented reality (AR) apps where multiple users interact within the same physical space are gaining in popularity (e.g., shared AR mode in Pokemon Go, virtual graffiti in Google's Just a Line). However, multi-user AR apps running over the cellular network can experience very high end-to-end latencies (measured at 12.5 s median on a public LTE network). To characterize and understand the root causes of this problem, we perform a first-of-its-kind measurement study on both public LTE and industry LTE testbed for two popular multi-user AR applications, yielding several insights: (1) The radio access network (RAN) accounts for a significant fraction of the end-to-end latency (31.2%, or 3.9 s median), resulting in AR users experiencing high, variable delays when interacting with a common set of virtual objects in off-the-shelf AR apps; (2) AR network traffic is characterized by large intermittent spikes on a single uplink TCP connection, resulting in frequent TCP slow starts that can increase user-perceived latency; (3) Applying a common traffic management mechanism of cellular operators, QoS Class Identifiers (QCI), can help by reducing AR latency by 33% but impacts non-AR users. Based on these insights, we propose network-aware and network-agnostic AR design optimization solutions to intelligently adapt IP packet sizes and periodically provide information on uplink data availability, respectively. Our solutions help ramp up network performance, improving the end-to-end AR latency and goodput by ~40-70%.

Evolved-Multimedia Broadcast Multicast Services (eMBMS) is a set of features in LTE networks to deliver bandwidth-intensive multimedia content on a point-to-multipoint basis to subscribers. The notion of a Single Frequency Network (SFN) in eMBMS allows base stations to synchronize and transmit signals in a coordinated fashion across the same frequency-time radio resources using a common modulation rate. While SFN boosts the channel quality of users via transmit diversity gain, the use of a common rate across base stations results in reduced utilization for those that can individually support much higher data rates for their users, even without the notion of an SFN. Excluding such base stations from the SFN helps them utilize their resources better by not being constrained by the common rate, but creates additional inter-cell interference from their independent transmissions. Striking a balance between SFN cooperation and resource utilization is crucial for efficiently delivering broadcast content as well as other unicast flows. We design BoLTE, which carefully addresses this tradeoff and evaluate it using a prototype implementation over an SFN testbed, realized over a cloud-based radio access network system, as well as large-scale NS3 simulations. We show that BoLTE improves overall system throughput by around 40%.

LTE-Advanced (LTE-A) macro-cell deployments are being enhanced with small cells, i.e., low-power base stations, to increase the network coverage and capacity. However, simultaneous co-channel transmissions from macro and small cells cause increased inter-cell interference and under-utilize the spectrum resources at the small cells. The following LTE-A design techniques are used to improve system performance in such deployments: (i) Carrier Aggregation (CA) to increase capacity by using additional carrier bandwidth; (ii) enhanced Inter-Cell Interference Coordination (elCIC), that includes (a) Cell Selection Biasing (CSB) to increase small cell spectrum utilization via cell range expansion; and (b) blanking data transmission on the macro cells for a certain duration of time to increase cell-edge user throughput Our objective is to maximize the CSB of the small cell, subject to user QoS constraints and blanking support from the macro cell. Towards this end, we develop an analytical model that captures the inter-dependency between elCIC techniques. We observe that, not accounting for the complex inter-dependencies between these techniques leads to a degraded network performance. We propose a framework that jointly optimizes elCIC and the assignment of multiple component carriers in an LTE-A deployment for increasing spectrum utilization at the small cells with appropriate blanking support from the macro cells. Our simulation results show that our approach increases the small cell spectrum utilization and aggregate cell-edge throughput by as much as 200%.

LTE network service reliability is highly dependent on the wireless coverage that is provided by cell towers (eNB). Therefore, the network operator's response to outage scenarios needs to be fast and efficient, in order to minimize any degradation in the Quality of Service (QoS). In this paper, we propose an outage mitigation framework for LTE-Advanced (LTE-A) wireless networks. Our framework exploits the inherent design features of LTE-A; it performs a dual optimization of the transmission power and beamforming weight parameters at each neighbor cell sector of the outage eNBs, while taking into account both the channel characteristics and residual eNB resources, after serving its current traffic load. Assuming statistical Channel State Information about the users at the eNBs, we show that this problem is theoretically NP-hard; thus we relax it as a convex optimization problem and solve for the optimal points using an iterative algorithm. Contrary to previously-proposed power control studies, our framework is specifically designed to alleviate the effects of sudden LTE-A eNB outages, where a large number of mobile users need to be efficiently offloaded to nearby towers. We present the detailed analytical design of our framework, and we assess its efficacy via extensive NS-3 simulations on an LTE-A topology. Our simulations demonstrate that our framework provides adequate coverage and QoS across all examined outage scenarios.

LTE-Advanced (LTE-A) systems support wider transmission bandwidths and hence, higher data rates for bulk traffic, as a result of Carrier Aggregation (CA). However, existing literature lacks efforts on channel-aware CA, especially in the uplink. The cell-edge users particularly suffer from exhaustion of resources, higher fading losses, lower SINR values (hence, requiring a higher power consumption) due to lossy channels that their traffic requirements are least-satisfied by channel-blind CA. This paper addresses the above concern by proposing an edge-prioritized channel- and traffic-aware uplink CA comprising Component Carrier (CC) assignment and resource scheduling. The LTE-A UEs are spatially-grouped and the under-represented edge UE groups, having the least assignable resources (good CCs), are prioritized for CA. This results in assigning the best channels to the edge groups. The frequency resources are scheduled to the groups based on inter-group and intra-group Proportional Fair Packet Scheduling (PFPS) in the time and frequency domains respectively, to resolve resource contention. The proposed approach outperforms the existing channel-blind Round-Robin and channel-aware Opportunistic CA, in terms of overall uplink throughput, by 33% in CC assignment and 21% in PFPS, in addition to significant throughput improvements for the edge UEs.

Ubiquitous integration of high-speed WLANs with wide-range 3GPP systems results in the service extension of the backbone cellular network. This paper envisions such heterogeneous wireless network architecture by integrating IEEE 802.11p VANETs with 3GPP LTE to achieve seamless data connectivity for uninterrupted multimedia sessions amongst spatially-apart vehicular clusters. Issues on cluster head-based multicasting and QoS are explored in this paper. An adaptive multi-metric Cluster Head (CH) election mechanism is proposed to manage the VANET sub-clusters. In addition to this, construction of a 2-hop virtual overlay mesh-based shared multicast tree for lower-level multicasting within VANETs is discussed. Following this, the process of VANET-LTE upper-level communication is detailed, addressing the issues of CH and gateway handover, and resource allocation of the LTE eNB. The envisioned architecture enables the LTE to effectively schedule multimedia sessions based on the service requirements of the VANET gateways, thus satisfying QoS. Requisite simulation results are presented to evaluate the integrated network.

Coupling the high data rates of IEEE 802.11p-based VANETs and the wide coverage area of 3GPP networks (e.g., UMTS), this paper envisions a VANET-UMTS integrated network architecture. In this architecture, vehicles are dynamically clustered according to different related metrics. From these clusters, a minimum number of vehicles, equipped with IEEE 802.11p and UTRAN interfaces, are selected as vehicular gateways to link VANET to UMTS. Issues pertaining to gateway selection, gateway advertisement and discovery, service migration between gateways (i.e., when serving gateways lose their optimality) are all addressed and an adaptive mobile gateway management mechanism is proposed. Simulations are carried out using NS2 to evaluate the performance of the envisioned architecture incorporating the proposed mechanisms. Encouraging results are obtained in terms of high data packet delivery ratios and throughput, reduced control packet overhead, and minimized delay and packet drop rates.

In this paper, a Multi-hop B3G architecture, which is a Heterogeneous Wireless Network (HWN) architecture, integrating MANET, Infrastructure WLAN with 3G UMTS network, is considered for the purpose of providing anytime, anywhere data access as it utilizes the higher bandwidth rates of MANET and WLAN networks and wider range of communication of 3G network. The issues of Gateways in HWN, which serve as a liaison between the MANET/WLAN and UMTS, are analyzed in this paper. A multi-metric Gateway Selection mechanism using Simple Additive Weighting (SAW) of MANET node metrics such as residual energy, 3G signal strength and mobility speed, is used to select an optimal Gateway from the dual-interface-enabled Gateway Candidates. As transaction progresses, when the above-mentioned metrics of the Gateway reach their respective pre-defined threshold values, thereby, affecting optimality of the current Gateway, a Multi-metric Adaptive Gateway Migration Mechanism (MAGMM) is proposed, which migrates the responsibility of the current Gateway to a newly-selected optimal Gateway, in order to sustain connectivity of the integrated network. This MAGMM is incorporated in the considered multi-hop B3G architecture and hence it is termed as Adaptive Gateway Management-based Multi-hop B3G Network (AGMMB3G) Architecture. In addition to MAGMM, this paper also compares AGMMB3G with the other existing HWN architectures. Simulations are carried out in HWN environment using NS2 and the results show how MAGMM enhances the overall HWN performance in terms of Transaction Duration, Packet Delivery Ratio and Control Packet Overhead parameters.