The highly heterogeneous ecosystem of Next Generation (NextG) wireless communication systems calls for novel networking paradigms where functionalities and operations can be dynamically and optimally reconfigured in real time to adapt to changing traffic conditions and satisfy stringent and diverse Quality of Service (QoS) demands. Open Radio Access Network (RAN) technologies, and specifically those being standardized by the O-RAN Alliance, make it possible to integrate network intelligence into the once monolithic RAN via intelligent applications, namely, xApps and rApps. These applications enable flexible control of the network resources and functionalities, network management, and orchestration through data-driven intelligent control loops. Recent work has showed how Deep Reinforcement Learning (DRL) is effective in dynamically controlling O-RAN systems. However, how to design these solutions in a way that manages heterogeneous optimization goals and prevents unfair resource allocation is still an open challenge, with the logic within DRL agents often considered as a opaque system. In this paper, we introduce PandORA, a framework to automatically design and train DRL agents for Open RAN applications, package them as xApps and evaluate them in the Colosseum wireless network emulator. We benchmark 23 xApps that embed DRL agents trained using different architectures, reward design, action spaces, and decision-making timescales, and with the ability to hierarchically control different network parameters. We test these agents on the Colosseum testbed under diverse traffic and channel conditions, in static and mobile setups. Our experimental results indicate how suitable fine-tuning of the RAN control timers, as well as proper selection of reward designs and DRL architectures can boost network performance according to the network conditions and demand. Notably, finer decision-making granularities can improve Massive Machine-Type Communications (mMTC)’s performance by$\sim\! 56\%$and even increase Enhanced Mobile Broadband (eMBB) Throughput by$\sim\! 99\%$.

Significant advances in wireless network technologies have given rise to use cases with unprecedented data rates, number of devices as well as low-latency constraints that thrive on such agility of networks. However, it also means that network management through appropriate resource allocation, coverage, and continuity of connection has become significantly more challenging compared to previous generations of networks. More recently, disaggregated network architectures have received increased attention through virtualization of important network functions and through the promise of significant value creation leveraging data-driven intelligent network control policies. In order to leverage the benefits of those versatile network technologies it is imperative that a fine balance be maintained between the resources allocated to a given set of users and the number of users that gain access to the network through intelligent admission control (AC). In this work, we propose and evaluate an admission control policy that leverages data-driven optimization to admit the maximum number of users while being acutely aware of quality of service (QoS) constraints of the users. This novel approach is achieved within the emerging O-RAN framework leveraging RAN Intelligent Controllers (RICs) to recommend appropriate policies enabling operators to maintain an efficient operating network. Our simulation results show that by intelligent tradeoff between the QoS and incoming UE request rejections, we can reduce the rejections by 2-3x in congested networks while maintaining acceptable QoS.

The highly heterogeneous ecosystem of Next Generation (NextG) wireless communication systems calls for novel networking paradigms where functionalities and operations can be dynamically and optimally reconfigured in real time to adapt to changing traffic conditions and satisfy stringent and diverse Quality of Service (QoS) demands. Open Radio Access Network (RAN) technologies, and specifically those being standardized by the O-RAN Alliance, make it possible to integrate network intelligence into the once monolithic RAN via intelligent applications, namely, xApps and rApps. These applications enable flexible control of the network resources and functionalities, network management, and orchestration through data-driven control loops. Despite recent work demonstrating the effectiveness of Deep Reinforcement Learning (DRL) in controlling O-RAN systems, how to design these solutions in a way that does not create conflicts and unfair resource allocation policies is still an open challenge. In this paper, we perform a comparative analysis where we dissect the impact of different DRL-based xApp designs on network performance. Specifically, we benchmark 12 different xApps that embed DRL agents trained using different reward functions, with different action spaces and with the ability to hierarchically control different network parameters. We prototype and evaluate these xApps on Colosseum, the world's largest O-RAN-compliant wireless network emulator with hardware-in-the-loop. We share the lessons learned and discuss our experimental results, which demonstrate how certain design choices deliver the highest performance while others might result in a competitive behavior between different classes of traffic with similar objectives.

Network slicing is one of the major catalysts to turn future telecommunication networks into versatile service platforms. Along with its benefits, network slicing is introducing new challenges in the development of sustainable network operations. In fact, guaranteeing slices requirements comes at the cost of additional energy consumption, in comparison to non-sliced networks. Yet, one of the main goals of operators is to offer the diverse 5G and beyond services, while ensuring energy efficiency. To this end, we study the problem of slice activation/deactivation, with the objective of minimizing energy consumption and maximizing the users quality of service (QoS). To solve the problem, we rely on two Multi-Armed Bandit (MAB) agents to derive decisions at individual base stations. Our evaluations are conducted using a real-world traffic dataset collected over an operational network in a medium size French city. Numerical results reveal that our proposed solutions provide approximately 11-14% energy efficiency improvement compared to a configuration where all the slice instances are active, while maintaining the same level of QoS. Moreover, our work explicitly shows the impact of prioritizing the energy over QoS, and vice versa.

The exponential growth of traffic in mobile networks is leading to increased pressure on the infrastructure of mobile networks and in particular on their backhaul networks. It is more critical than ever to carefully plan backhaul networks. In this paper, we formulate and solve the problem of hierarchical wireless backhaul network design. In formulating our problem, we cover different requirements, namely: topology simplicity, network resiliency, and link reliability. We formulate the problem as an Integer Linear Programming (ILP) problem, allowing us to solve the problem to optimality. Furthermore, we provide a graph theory-based algorithm that allows solving the problem over a large scale. The proposed algorithm exploits the properties of the graph that represents the network. The results of our evaluations in various network scenarios demonstrate the efficiency of our ILP formulation and the proposed algorithm in keeping the backhaul network simple, resilient, and reliable. Using a practical channel propagation model and different node densities that are representative of small-scale and large-scale urban environments, our results also show that even with high resiliency requirements, the network traffic can be backhauled with only 5-10% of the nodes for the considered densities. Our results also demonstrate that our algorithm leads to near-optimal solutions in different scenarios.

The problem of selecting the modulation and coding scheme (MCS) that maximizes the system throughput, known as link adaptation, has been investigated extensively, especially for IEEE 802.11 (WiFi) standards. Recently, deep learning has widely been adopted as an efficient solution to this problem. However, in failure cases, predicting a higher-rate MCS can result in a failed transmission. In this case, a retransmission is required, which largely degrades the system throughput. To address this issue, we model the adaptive modulation and coding (AMC) problem as a multi-label multi-class classification problem. The proposed modeling allows more control over what the model predicts in failure cases. We also design a simple, yet powerful, loss function to reduce the number of retransmissions due to higher-rate MCS classification errors. Since wireless channels change significantly due to the surrounding environment, a huge dataset has been generated to cover all possible propagation conditions. However, to reduce training complexity, we train the CNN model using part of the dataset. The effect of different subdataset selection criteria on the classification accuracy is studied. The proposed model adapts the IEEE 802.11ax communications standard in outdoor scenarios. The simulation results show the proposed loss function reduces up to 50% of retransmissions compared to traditional loss functions.

In this paper, we analyze the weather information for 14 waterbodies from geographical areas with different meteorological characteristics. We estimate the sub-hourly instances of the evaporation duct height (EDH) throughout a period of 10 years. Then, considering the frequency range 1 to 6 GHz, based on the parabolic equation method, we analyze the quality for a presumed shore-to-ship link throughout 100 km range. We evaluate the maximum range that can be supported for different reliability requirements and we focus specifically on analyzing the gain that can be obtained when antenna height and/or band diversity are used. It was found that for high reliability requirements, the antenna height at the shore is the main factor on deciding the maximum communication range that can be maintained. On the other hand, for applications that tolerate delay and work seasonally on an opportunistic basis, the evaporation duct statistics is the main factor deciding the likelihood of increasing the link range and establishing over-the-horizon communications.

In the context of outdoor localization over systems impaired by non-line of sight (NLoS), the minimum error entropy with fiducial points (MEE-FP) based methods have emerged as promising due to their excellent generalization and independence to statistics of NLoS. However, the performance of these approaches are well-known to depend on hyperparameters, such as, the spread parameter of the MEE-FP criterion. To enable MEEFP based hyperparameter-free localization, we propose a modified Gauss-Newton based localization algorithm based on sampled kernel-widths. Next, analytical results are derived to demonstrate the asymptotic equivalence of the proposed kernel-width sampling based localization algorithm to its ideal fixed kernel width based counterpart. This equivalence is validated through computer simulations assuming typical non-Gaussian NLoS distributions, which motivates the hyperparameter-independence of the proposed localization algorithm and its generalization to different NLoS statistics.

Adopting OFDMA and MU-MIMO techniques for both downlink and uplink IEEE 802.11ax will help next-generation WLANs efficiently cope with large numbers of devices but will also raise some research challenges. One of these is how to optimize the channelization, resource allocation, beamforming design, and MCS selection jointly for IEEE 802.11ax-based WLANs. In this paper, this technical requirement is formulated as a mixed-integer non-linear programming problem maximizing the total system throughput for the WLANs consisting of unicast users with multicast groups. A novel two-stage solution approach is proposed to solve this challenging problem. The first stage aims to determine the precoding vectors under unit-power constraints. These temporary precoders help re-form the main problem into a joint power and radio resource allocation one. Then, two low-complexity algorithms are proposed to cope with the new problem in stage two. The first is developed based on the well-known compressed sensing method while the second seeks to optimize each of the optimizing variables alternatively until reaching converged outcomes. The outcomes corresponding to the two stages are then integrated to achieve the complete solution. Numerical results are provided to confirm the superior performance of the proposed algorithms over benchmarks.

Coded orthogonal frequency-division multiplexing (COFDM) is a popular modulation technique for wireless communication that guarantees reliable transmission of data over noisy wireless channels. However, a major disadvantage in implementing it is its resulting high peak to average power ratio (PAPR). Including forward error correction (FEC) in the orthogonal frequency division multiplexing (OFDM) system enables the avoidance of transmission errors. Nevertheless, the selected code may impact the value of PAPR. The objective of this paper is to analyze the impact of FEC on the PAPR for the COFDM system based on the autocorrelation of the signal, before the inverse fast Fourier transform (IFFT) block in the COFDM system, the evaluation of the complementary cumulative distribution function (CCDF) of PAPR, and the bit error rate (BER). The autocorrelation of the COFDM system is calculated based on a Markov chain model. From the results, we can reach a conclusion on the characteristics we need to consider in order to choose the codes relating to the PAPR performance in the COFDM system.

LTE Device-to-device (D2D) discovery and communication has been considered a means to allow capacity offloading, range extension as well as commercial proximity services such as advertisement or social networking. Within this context, several service discovery approaches may be envisioned. In this paper, we study strategies which rely on a central function supporting service discovery between LTE UEs by push or pull mechanisms. We propose some simplified models to compare them in terms of control overhead and UE energy consumption. Then we propose and evaluate a new approach which combines both PUSH and PULL strategies and highlight the gain that can be achieved on service discovery performances.

Constant-amplitude transmitter architectures offer high amplification efficiencies by using one or more nonlinear amplifiers. In this article, we propose one new such architecture, dubbed DbPSK, for efficient MQAM transmission. The proposed architecture decomposes the MQAM constellation into two pseudo-MPSK constellations that are independently amplified, with high efficiency nonlinear amplifiers, then combined to generate the original MQAM signal amplified. We show that the proposed architecture provides interesting performance in terms of power, efficiency and linearity for any MQAM signal transmission and we discuss its implementation aspects. This architecture can be considered as an improvement of the NLA-QAM architecture used in satellite applications.