By aggregating multiple channels, Carrier Aggregation (CA) is an important technology for boosting cellular network bandwidth. Given diverse radio bands made available in 5G networks, CA plays a particularly critical role in achieving the goal of multi-Gbps throughput performance. In this paper, we carry out a timely comprehensive measurement study of CA deployment in commercial 5G networks (as well as 4G networks). We identify the key factors that influence whether CA is deployed and when, as well as which band combinations are used. Thus, we reveal the challenges posed by CA in 5G performance analysis and prediction as well as their implications in application quality-of-experience (QoE). We argue for and develop a novel CA-aware deep learning framework, dubbed Prism5G, which explicitly accounts for the complexity introduced by CA to more effectively predict 5G network throughput performance. Through extensive evaluations, we demonstrate the superiority of Prism5G over existing throughput prediction algorithms. Prism5G improves 5G throughput prediction accuracy by over 14% on average and a maximum of 22%. Using two use cases as examples, we further illustrate how Prism5G can aid applications in optimizing QoE performance.

Unlike previous generation cellular technologies, 5G networks support diverse radio bands from low-band, mid-band to (mmWave) high-band, and offer a wide variety of new and enhanced features. In particular, 3GPP 5G standards adopt a flow-based 5G Quality-of-Service (QoS) framework that allows more flexibility in mapping QoS "flows" to data radio bearers. Nonetheless, the 5G QoS classes are pre-defined and QoS treatment is limited to the "flow" level. As we will argue in an earlier paper, the 5G QoS framework cannot fully and intelligently utilize the diversity of 5G radio bands and other capabilities to cope with fast varying channel conditions, and is therefore inadequate in meeting the quality-of-experience (QoE) requirements of many emerging applications such as augmented/virtual realities (AR/VR) and connected and autonomous vehicles (CAV). This has led us to advance a novel software-defined, fine-grained QoS framework for 5G/NextG networks.In this "work in progress" paper, we share our initial experience in prototyping the proposed fine-grained QoS framework. Our framework extends both the 5G core network and 5G radio access network (RAN) functionality to enable intelligent control of radio resources in a fashion that exploits application semantics to improve user QoE. We discuss in detail about the changes in different systems and its individual components, share the current state of implementation progress (work completed and in-progress) and finally our evaluation plan to validate the framework when the implementation is complete.

As the plethora of Internet of Things (IoT) devices gradually make their way into our lives, several Cloud Service Providers (CSPs) have developed IoT gateway platforms (SDKs) that solely connects IoT devices to their respective cloud. Such gateways have 1) cumbersome IoT device configuration; 2) inflexible IoT data managements; and 3) support no/little cross-vendor edge computation and cloud analytics. We term these commercial gateway SDKs as cloud-centric. In this paper, we study the state-of-the-art vendor-locked IoT Gateway solutions and approaches and propose an edge-centric paradigm through an evolutionary framework, dubbed VeerEdge for developing IoT gateways. We leverage computing and storage capabilities at the network edge for edge-based device & IoT service management and data processing. We exploit availability of multiple cloud services for "best" IoT data analytics. Evaluation results show that VeerEdge achieves this with negligible overhead in terms of latency, CPU and RAM usage when compared to state-of-the-art industrial IoT gateways.

The emerging 5G services offer numerous new opportunities for networked applications. In this study, we seek to answer two key questions: i) is the throughput of mmWave 5G predictable, and ii) can we build "good" machine learning models for 5G throughput prediction? To this end, we conduct a measurement study of commercial mmWave 5G services in a major U.S. city, focusing on the throughput as perceived by applications running on user equipment (UE). Through extensive experiments and statistical analysis, we identify key UE-side factors that affect 5G performance and quantify to what extent the 5G throughput can be predicted. We then propose Lumos5G -- a composable machine learning (ML) framework that judiciously considers features and their combinations, and apply state-of-the-art ML techniques for making context-aware 5G throughput predictions. We demonstrate that our framework is able to achieve 1.37X to 4.84X reduction in prediction error compared to existing models. Our work can be viewed as a feasibility study for building what we envisage as a dynamic 5G throughput map (akin to Google traffic map). We believe this approach provides opportunities and challenges in building future 5G-aware apps.