Internet of Things applications require timely access to information collected from sensors deployed over large geographic areas. However, such applications often experience highly-varying network conditions that prevent the timely delivery of information updates related to source data from sensors. Moreover, IoT applications have different metrics of interest and patterns to request source data. This article explicitly addresses the timely delivery of information updates in heterogeneous IoT scenarios with different application-specific goals. For this purpose, it introduces new metrics based on age of information (AoI) to accurately describe timeliness of updates in such a context. Moreover, it analytically derives optimal update generation policies for different request patterns to minimize the overall update age in an IoT system and maximize fairness of updates. Finally, it carries out a thorough performance evaluation of the proposed policies for representative request patterns with a real-world dataset of Internet connectivity. The obtained results demonstrate that the proposed policies are competitive with those in the state of the art, with a two order of magnitude reduction in energy consumption and up to a$\mathbf{1 9. 9 \%}$higher fairness.

The energy consumption of 5G base stations (BSs) is significantly higher than that of 4G BSs, creating challenges for operators due to increased costs and carbon emissions. Existing solutions address this issue by switching off BSs during specific periods or forming cooperation coalitions where some BSs deactivate while others serve users. However, these approaches often rely on fixed geographic configurations, making them unsuitable for urban areas with numerous BSs and mobile users. To tackle these challenges, we propose a hierarchical reinforcement learning (RL) framework for energy conservation in large-scale 5G networks. In the upper-layer, we propose a deep Q-network integrated with a graph convolutional network that dynamically groups BSs into coalitions from a macro perspective. This layer focuses on high-level coalition formation to optimize system-wide energy efficiency by considering the global state of the network. In the lower-layer, we combine attention mechanism with multi-agent RL and graph convolutional networks to design a scalable algorithm that maximizes local energy efficiency through optimizing the cooperation within each coalition. These two layers align global coalition dynamics with local intra-coalition cooperation to achieve system-wide energy optimization. Moreover, we accurately model large-scale urban 5G scenarios leveraging a high-fidelity network simulator, which enables our RL framework to learn from real-world feedback. Extensive experiments conducted with the simulator demonstrate that our proposed framework achieves remarkable energy savings of up to 75.6%, significantly outperforming baseline approaches. These findings highlight the effectiveness and superiority of our hierarchical RL optimization framework in addressing the energy consumption challenges faced by large-scale 5G networks.

Mobile devices are expected to be always connected, and this implies that the mobile network is able to quickly identify and address faults that impact service (for example, due to power outages). In this article, we present our approach for automatically detecting mass power outages. Our solution decreases the number of created trouble tickets in two mobile networks by 4.7% and 9.3%.

Long range (LoRa) is one of the most popular technologies for low-power wide area networks. It offers long-range communication with a low energy consumption, which makes it ideal for many applications in the Internet of Things. The performance of LoRa networks depends on the communication parameters used by individual nodes. Several works have proposed different solutions, typically running on a central network server, to select these parameters. However, existing approaches have not addressed the need to (re-)assign parameters when channel conditions suddenly vary due to additional traffic, changes in the weather or the presence of obstacles. Moreover, allocation strategies that require a central entity to decide communication parameters do not scale due to the large number of configuration packets that must be sent to the nodes. To address these issues, this article proposesNoReL, a distributed game-theoretic approach that allows nodes to autonomously update their parameters and maximize their packet delivery ratio.NoReLis based on a stochastic variant of no-regret learning, which is proven to reach an$\epsilon$-coarse correlated equilibrium in LoRa networks. Extensive simulations show thatNoReLachieves a higher delivery ratio than the state of the art in both static and dynamic environments, with an improvement up to 12%.

Edge computing is a promising solution to host artificial intelligence (AI) applications that enable real-time insights on user-generated and device-generated data. This requires edge computing resources (storage and compute) to be widely deployed close to end devices. Such edge deployments require a large amount of energy to run as edge resources are typically overprovisioned to flexibly meet the needs of time-varying user demand with a low latency. Moreover, AI applications rely on deep neural network (DNN) models that are increasingly larger in size to support high accuracy. These DNN models must be efficiently stored and transferred, so as to minimize their energy consumption. In this article, we model the problem of energy-efficient placement of services (namely, DNN models) for AI applications as a multiperiod optimization problem. The formulation jointly places services and schedules requests such that the overall energy consumption is minimized and latency is low. We propose a heuristic that efficiently solves the problem while taking into account the impact of placing services across time periods. We assess the quality of the proposed heuristic by comparing its solution to a lower bound of the problem, obtained by formulating and solving a Lagrangian relaxation of the original problem. Extensive simulations show that our proposed heuristic outperforms baseline approaches in achieving a low energy consumption by packing services on a minimal number of edge nodes, while at the same time keeping the average latency of served requests below a configured threshold in nearly all time periods.

Long Range (LoRa) is a low-power wireless communication technology for long-range connectivity, extensively used in the Internet of Things. Several works in the literature have analytically characterized the performance of LoRa networks, with particular focus on scalability and reliability. However, most of the related models are limited, as they cannot account for factors that occur in practice, or make strong assumptions on how devices are deployed in the network. This article proposes an analytical model that describes the delivery ratio in a LoRa network with device-level granularity. Specifically, it considers the impact of several key factors that affect real deployments, including multiple gateways and channel variation. Therefore, the proposed model can effectively evaluate the delivery ratio in realistic network topologies, without any restrictions on device deployment or configuration. It also accurately characterizes the delivery ratio of each device in a network, as demonstrated by extensive simulations in a wide variety of conditions, including diverse networks in terms of node deployment and link-level parameter settings. The proposed model provides a level of detail that is not available in the state of the art, and it matches the simulation results within an error of a few percentage points.

The energy consumption of mobile networks is already substantial nowadays, and only expected to further increase with the roll-out of 5G. Base stations are the key elements in this context: reducing their energy consumption is of paramount importance for network operators, not only to lower operating costs, but also to meet sustainable development goals. Today's base stations are typically over-provisioned, i.e., they comprise multiple cells to meet the peak load in a region. Therefore, substantial energy savings are possible by switching off cells that are under-utilized. This article proposes a data-driven approach to determine the time periods when a cell can be switched off. Forecasting is used to accurately predict network utilization and automatically find the time intervals to reliably switch off a cell. We carefully analyze the requirements of the system as a whole, from data collection to forecasting methods, to enable effective energy savings in practice. Considering several real-world traces from LTE networks, we show that an average of 10.24% energy savings is possible. We explore the trade-offs between energy savings and overhead in switching off cells, and provide insights into the choice of methods accordingly. In particular, we show that the accuracy of forecasting is not the most important factor in achieving energy savings; instead, the prediction (uncertainty) interval plays a key role in being able to achieve energy savings with less impact on end-users. Finally, we propose a model to generate utilization traces that match the distribution of real-world traces obtained from cellular networks.

Long range (LoRa) is a wireless communication standard specifically targeted for resource-constrained Internet of Things (IoT) devices. LoRa is a promising solution for smart city applications as it can provide long-range connectivity with a low energy consumption. The number of LoRa-based networks is growing due to its operation in the unlicensed radio bands and the ease of network deployments. However, the scalability of such networks suffers as the number of deployed devices increases. In particular, the network performance drops due to increased contention and interference in the unlicensed LoRa radio bands. This results in an increased number of dropped messages and, therefore, unreliable network communications. Nevertheless, network performance can be improved by appropriately configuring the radio parameters of each node. To this end, in this article we formulate integer linear programming models to configure LoRa nodes with the optimal parameters that allow all devices to reliably send data with a low energy consumption. We evaluate the performance of our solutions through extensive network simulations considering different types of realistic deployments. We find that our solution consistently achieves a higher delivery ratio (up to 8% higher) than the state of the art with minimal energy consumption. Moreover, the higher delivery ratio is achieved by a large percentage of nodes in each network, thereby resulting in a fair allocation of radio resources. Finally, the optimal network configurations are obtained within a short time, usually much faster than the state of the art. Thus, our solution can be readily used by network operators to determine optimal configurations for their IoT deployments, resulting in improved network reliability.

Recent advancements in virtualization and software architecture have led to the new paradigm of serverless computing, which allows developers to deploy applications as stateless functions without worrying about the underlying infrastructure. Accordingly, a serverless platform handles the lifecycle, execution and scaling of the actual functions; these need to run only when invoked or triggered by an event. Thus, the major benefits of serverless computing are low operational concerns and efficient resource management and utilization. Serverless computing is currently offered by several public cloud service providers. However, there are certain limitations on the public cloud platforms, such as vendor lock-in and restrictions on the computation of the functions. Open source serverless frameworks are a promising solution to avoid these limitations and bring the power of serverless computing to on-premise deployments. However, these frameworks have not been evaluated before. Thus, we carry out a comprehensive feature comparison of popular open source serverless computing frameworks. We then evaluate the performance of selected frameworks: Fission, Kubeless and OpenFaaS. Specifically, we characterize the response time and ratio of successfully received responses under different loads and provide insights into the design choices of each framework.

Vehicular applications in smart cities, including assisted and autonomous driving, require complex data processing and low-latency communication. An effective approach to address these demands is to leverage the edge computing paradigm, wherein processing and storage resources are placed at access points of the vehicular network, i.e., at roadside units (RSUs). Deploying edge computing devices for vehicular applications in urban scenarios presents two major challenges. First, it is difficult to ensure continuous wireless connectivity between vehicles and RSUs, especially in dense urban areas with many buildings. Second, edge computing devices have limited processing resources compared to the cloud, thereby requiring careful network planning to meet the computational and latency requirements of vehicular applications. This article specifically addresses these challenges. In particular, it targets efficient deployment of edge computing devices in an urban scenario, subject to application- specific quality of service constraints. To this end, this article introduces a mixed integer linear programming formulation to minimize the deployment cost of edge devices by jointly satisfying a target level of network coverage and computational demand. The proposed approach is able to accurately model complex urban environments with many buildings and a large number of vehicles. Furthermore, this article presents a simple yet effective heuristic to deploy edge computing devices based on the knowledge of road traffic in the target deployment area. The devised methods are evaluated by extensive simulations with data from the city of Dublin. The obtained results show that the proposed solutions can effectively guarantee a target application- specific quality of service in realistic conditions.

Large-scale Internet of Things (IoT) deployments demand long-range wireless communications, especially in urban and metropolitan areas. LoRa is one of the most promising technologies in this context due to its simplicity and flexibility. Indeed, deploying LoRa networks in dense IoT scenarios must achieve two main goals: efficient communications among a large number of devices and resilience against dynamic channel conditions due to demanding environmental settings (e.g., the presence of many buildings). This work investigates adaptive mechanisms to configure the communication parameters of LoRa networks in dense IoT scenarios. To this end, we develop FLoRa, an open-source framework for end-to-end LoRa simulations in OMNeT++. We then implement and evaluate the Adaptive Data Rate (ADR) mechanism built into LoRa to dynamically manage link parameters for scalable and efficient network operations. Extensive simulations show that ADR is effective in increasing the network delivery ratio under stable channel conditions, while keeping the energy consumption low. Our results also show that the performance of ADR is severely affected by a highly-varying wireless channel. We thereby propose an improved version of the original ADR mechanism to cope with variable channel conditions. Our proposed solution significantly increases both the reliability and the energy efficiency of communications over a noisy channel, almost irrespective of the network size. Finally, we show that the delivery ratio of very dense networks can be further improved by using a network-aware approach, wherein the link parameters are configured based on the global knowledge of the network.

The amount of data generated by sensors, actuators, and other devices in the Internet of Things (IoT) has substantially increased in the last few years. IoT data are currently processed in the cloud, mostly through computing resources located in distant data centers. As a consequence, network bandwidth and communication latency become serious bottlenecks. This paper advocates edge computing for emerging IoT applications that leverage sensor streams to augment interactive applications. First, we classify and survey current edge computing architectures and platforms, then describe key IoT application scenarios that benefit from edge computing. Second, we carry out an experimental evaluation of edge computing and its enabling technologies in a selected use case represented by mobile gaming. To this end, we consider a resource-intensive 3-D application as a paradigmatic example and evaluate the response delay in different deployment scenarios. Our experimental results show that edge computing is necessary to meet the latency requirements of applications involving virtual and augmented reality. We conclude by discussing what can be achieved with current edge computing platforms and how emerging technologies will impact on the deployment of future IoT applications.

Network Functions Virtualization (NFV) consists of implementing network functions as software applications that can run on general-purpose servers. This paper discusses the application of NFV to the Mobility Management Entity (MME), a control plane entity in the Evolved Packet Core (EPC). With the convergence of cloud computing and mobile networks, conventional architectures of network elements need to be re-designed in order to fully harness benefits such as scalability and elasticity. To this end, we design and implement a distributed MME with the three-tier architecture common to web applications. We deploy the components of the distributed MME on two separate OpenStack clouds and evaluate the latency of the attach procedure. We find that the placement of the components within the data center significantly affects the attach latency.