Real time control of connected industry devices such as mobile robots constituting Industrial Internet of Things (IIoT) has made time-sensitive communications over Wi-Fi increasingly important. In order to provide support for time-sensitive services over Wi-Fi, key features of the IEEE 802.11 standard such as restricted Target Wake Time (rTWT) and multi-user Orthogonal Frequency Division Multiple Access (OFDMA) can be exploited. However, even with rTWT and OFDMA, Time-Sensitive Networking (TSN) over Wi-Fi is still a challenge given the unpredictability of wireless channels and the increasing number of Wi-Fi-enabled devices. In this paper, we present a comprehensive network calculus-based analysis of the delay bounds achievable in Wi-Fi networks, leveraging these IEEE 802.11 enhancements alongside synchronized priority queuing via IEEE 802.1Qbv. We propose PONTE, a novel Fully Polynomial Time Approximation Scheme (FPTAS) scheduler that guarantees strict non-violation probabilities (e.g., 99.99%) for inelastic, time-critical traffic over an 802.11 wireless network. Our extensive analysis and simulations in an IIoT scenario demonstrate that PONTE effectively manages dense, mixed traffic flows, achieving TSN objectives with minimal impact on fairness. Our approach is two orders of magnitude faster than the state-of-the-art.

The rising popularity of Vehicle-to-Network (V2N) applications is driven by the Ultra-Reliable Low-Latency Communications (URLLC) service offered by 5G. Distributed resources can help manage heavy traffic from these applications, but complicate traffic routing under URLLCfs strict delay requirements. In this paper, we introduce the V2N Computation Offloading and CPU Activation (V2N-COCA) problem, aiming at the monetary/energetic cost minimization via computation offloading and edge/cloud CPU activation decisions, under stringent latency constraints. Some challenges are the proven nonmonotonicity of the objective function and the no-existence of closed-formulas for the sojourn time of tasks. We present a provably tight approximation for the latter, and we design BiQui, a provably asymptotically optimal and computationally efficient algorithm for the V2N-COCA problem. We then study dynamic scenarios, introducing the Swap-Prevention problem, to account for changes in the traffic load and minimize the switching on/off of CPUs without incurring into overcosts.We prove the problemfs structural properties and exploit them to design Min-Swap, a provably correct and computationally effective algorithm for the Swap-Prevention Problem. We assess both BiQui and Min-Swap over real-world vehicular traffic traces, performing a sensitivity analysis and a stress-test. Results show that (i) BiQui is nearoptimal and significantly outperforms existing solutions; and (ii) Min-Swap reduces by a ≥90% the CPU swapping incurring into just ≤0.14% extra cost.

Cellular Vehicle-to-Everything (C-V2X) is currently at the forefront of the digital transformation of our society. By enabling vehicles to communicate with each other and with the traffic environment using cellular networks, we redefine transportation, improving road safety and transportation services, increasing the efficiency of vehicular traffic flows, and reducing environmental impact. To effectively facilitate the provisioning of Cellular Vehicular-to-Network (C-V2N) services, we tackle the interdependent problems of service task placement and scaling of edge resources. Specifically, we formulate the joint problem and prove that it is not computationally tractable. To address its complexity we propose dhpg, a new Deep Reinforcement Learning (DRL) approach that operates in hybrid action spaces, enabling holistic decision-making and enhancing overall performance. We evaluated the performance of DHPG using simulations with a real-world C-V2N traffic dataset, comparing it to several state-of-the-art (SoA) solutions. DHPG outperforms these solutions, guaranteeing the 99th percentile of C-V2N service delay target, while simultaneously optimizing the utilization of computing resources. Finally, time complexity analysis is conducted to verify that the proposed approach can support real-time C-V2N services.

The rising popularity of Vehicle-to-Network (V2N) applications is driven by the Ultra-Reliable Low-Latency Communications (URLLC) service offered by 5G. The availability of distributed resources could be leveraged to handle the enormous traffic arising from these applications, but introduces complexity in deciding where to steer traffic under the stringent delay requirements of URLLC. In this paper, we introduce the V2N Computation Offloading and CPU Activation (V2N-COCA) problem, which aims at finding the computation offloading and the edge/cloud CPU activation decisions that minimize the operational costs, both monetary and energetic, under stringent latency constraints. Some challenges are the proven non-monotonicity of the objective function w.r.t. offloading decisions, and the no-existence of closed-formulas for the sojourn time of tasks. We present a provably tight approximation for the latter, and we design BiQui, a provably asymptotically optimal and with linear computational complexity w.r.t. computing resources algorithm for the V2N-COCA problem. We assess BiQui over real-world vehicular traffic traces, performing a sensitivity analysis and a stress-test. Results show that BiQui significantly outperforms state-of-the-art solutions, achieving optimal performance (found through exhaustive searches) in most of the scenarios.

Tele-operated Driving (ToD) is an ambitious use case in the automotive sector that enables the remote operation of vehicles, e.g., when they are located in dangerous environments, for logistics fleet operations. ToD heavily relies on 5G connectivity able to guarantee strict latency, reliability, and bandwidth requirements, for instance through a dedicated network slice. In this paper, we propose a Digital Twin (DT)-assisted radio resource allocation scheme that manages the Radio Access Network (RAN) resources within the ToD network slice. In particular, our contributions leverage interactions between the DT of the RAN and of other ToD players to feed an algorithm for efficient radio resource allocation, based on the actual ToD service demand on the planned driving paths. Early results on a realistic map demonstrate the resource savings achieved by our proposal compared to a static resource allocation scheme.

Industry 4.0 applications impose the challenging demand of delivering packets with bounded latencies via a wireless network. This is further complicated if the network is not dedicated to the time critical application. In this paper we use network calculus analysis to derive closed form expressions of latency bounds for time critical traffic when 802.11 Target Wake Time (TWT) and 802.1Qbv work together in a shared 802.11 network.

Recent trends in robotic services propose offloading robot functionalities to the Edge to meet the strict latency requirements of networked robotics. However, the Edge is typically an expensive resource and sometimes the Cloud is also an option, thus, decreasing the cost. Following this idea, we propose Don’t Let Me Down! (DLMD), an algorithm that promotes offloading robot functions to the Cloud when possible to minimize the consumption of Edge resources. Additionally, DLMD takes the appropriate migration, traffic steering, and radio handover decisions to meet robotic service requirements as strict latency constraints. In the paper, we formulate the optimization problem that DLMD aims to solve, compare DLMD performance against the state of the art, and perform stress tests to assess DLMD performance in small & large networks. Results show that DLMD (i) always finds solutions in less than 30ms; (ii) is optimal in a local warehousing use case; and (iii) consumes only 5% of the Edge resources upon network stress.

In this demonstration, FoReCo is introduced as a solution for recovering lost control commands in remotely controlled robots. Visitors are given the opportunity to remotely control a robotic arm using a joystick, with the added challenge of experiencing packet losses in the wireless medium. The lost control commands cause the robotic arm’s trajectory to become distorted. To combat this issue, FoReCo is implemented and utilizes an ML model that has been trained on a real-world dataset to recover the lost control commands. The demonstration illustrates how FoReCo recovers the lost commands, resulting in the robotic arm operating smoothly despite the presence of wireless medium losses.

The fifth generation (5G) of wireless networks is set out to meet the stringent requirements of vehicular use cases. Edge computing resources can aid in this direction by moving processing closer to end-users, reducing latency. However, given the stochastic nature of traffic loads and availability of physical resources, appropriate auto-scaling mechanisms need to be employed to support cost-efficient and performant services. To this end, we employ Deep Reinforcement Learning (DRL) for vertical scaling in Edge computing to support vehicular-to-network communications. We address the problem using Deep Deterministic Policy Gradient (DDPG). As DDPG is a model-free off-policy algorithm for learning continuous actions, we introduce a discretization approach to support discrete scaling actions. Thus we address scalability problems inherent to high-dimensional discrete action spaces. Employing a real-world vehicular trace data set, we show that DDPG outperforms existing solutions, reducing (at minimum) the average number of active CPUs by 23% while increasing the long-term reward by 24%.

Ongoing research and industrial exploitation of SDN and NFV technologies promise higher flexibility on network automation and infrastructure optimization. Choosing the location of Virtual Network Functions is a central problem in the automation and optimization of the software-defined, virtualization-based next generation of networks such as 5G and beyond. Network services provided for autonomous vehicles, factory automation, e-health and cloud robotics often require strict delay bounds and reliability constraints influenced by the location of its composing Virtual Network Functions. Robots, vehicles and other end-devices provide significant capabilities such as actuators, sensors and local computation which are essential for some services. Moreover, these devices are continuously on the move and might lose network connection or run out of battery, which further challenge service delivery in this dynamic environment. This work tackles the mobility, and battery restrictions; as well as the temporal aspects and conflicting traits of reliable, low latency service deployment over a volatile network, where mobile compute nodes act as an extension of the cloud and edge computing infrastructure. The problem is formulated as a cost-minimizing Virtual Network Function placement optimization and an efficient heuristic is proposed. The algorithms are extensively evaluated from various aspects by simulation on detailed real-world scenarios.

Wireless communications represent a game changer for future manufacturing plants, enabling flexible production chains, as machinery and other components not to be restricted to a location by the rigid wired connections on the factory floor. However, the presence of electromagnetic interference in the wireless spectrum may result in packet loss and delay, making it a challenging environment to meet the extreme reliability requirements of industrial applications. In such conditions, achieving real-time remote control, either from the Edge or Cloud, becomes complex. In this paper, we investigate a forecast-based recovery mechanism for real-time remote control of robotic manipulators (FoReCo) that uses Machine Learning (ML) to infer lost commands caused by interference in the wireless channel. FoReCo is evaluated through both simulation and experimentation in interference prone IEEE 802.11 wireless links, and using a commercial research robot that performs pick-and-place tasks. Results show that upon interference FoReCo reduces the trajectory error by more than a 34.35% in both simulation, and experimentation. We also show that FoReCo is sufficiently lightweight to be deployed in existing hardware.

Thanks to network slicing, mobile networks can now support multiple and diverse services, each requiring different key performance indicators (KPIs). In this new scenario, it is critical to allocate network and computing resources efficiently and in such a way that all KPIs targeted by a service are met. Accounting for all sorts of KPIs (e.g., availability and reliability, besides the more traditional throughput and latency) is an aspect that has been scarcely addressed so far and that requires tailored models and solution strategies. We address this issue by proposing a novel methodology and resource orchestration scheme, named OKpi, which provides high-quality decisions on VNF (Virtual Network Function) placement and data routing, including the selection of radio points of attachment. Importantly, OKpi has polynomial computational complexity and accounts forallKPIs required by each service, and for any resource available from the fog to the cloud. We prove several properties of OKpi and demonstrate that it performs very closely to the optimum under real-world scenarios. We also implement OKpi in a testbed supporting a robot-based, smart factory service, and we present some field tests that further confirm the ability of OKpi to make high-quality decisions.

This paper proposes a dynamic pricing and revenue-driven service federation strategy based on a Deep Q-Network (DQN) to instantly and automatically decide federation across different service provider domains, each introduces dynamic service prices offering to its customers and towards other domains. A dynamic pricing model is considered in this work based on the analysis of real pricing data collected from public cloud provider, and upon this a dynamic arrival process as a result of the price changes is proposed for formulating the service federation problem as a Markov Decision Problem (MDP). In this work, several reinforcement learning algorithms are developed to solve the problem, and the presented results show that the DQN method reached 90% of the optimal revenue and outperformed existing state-of-the-art strategies, and it can learn the federation pricing dynamics to make optimum federation decisions according to price changes.

5G networks aim to provide orchestration of services across multiple administrative domains through the concept of federation. In this paper, we are exploring the federation feature of a platform for 5G transport network of vertical services. Then we formulate the decision problem that directly impacts the revenue of 5G administrative domains, and we propose as solution a Q-learning algorithm. The simulation results show near optimum profit maximization and a well-trained Q-learning algorithm can outperform the intuitive “greedy” approach in a realistic scenario.

Networks can now process data as well as transporting it; it follows that they can support multiple services, each requiring different key performance indicators (KPIs). Because of the former, it is critical to efficiently allocate network and computing resources to provide the required services, and, because of the latter, such decisions must jointly consider all KPIs targeted by a service. Accounting for newly introduced KPIs (e.g., availability and reliability) requires tailored models and solution strategies, and has been conspicuously neglected by existing works, which are instead built around traditional metrics like throughput and latency. We fill this gap by presenting a novel methodology and resource allocation scheme, named OKpi, which enables high-quality selection of radio points of access as well as VNF (Virtual Network Function) placement and data routing, with polynomial computational complexity. OKpi accounts for all relevant KPIs required by each service, and for any available resource from the fog to the cloud. We prove several important properties of OKpi and evaluate its performance in two real-world scenarios, finding it to closely match the optimum.

The future 5G transport networks are envisioned to support a variety of vertical services through network slicing and efficient orchestration over multiple administrative domains. In this paper, we propose an orchestrator architecture to support vertical services to meet their diverse resource and service requirements. We then present a system model for resource orchestration of transport networks as well as low-complexity algorithms that aim at minimizing service deployment cost and/or service latency. Importantly, the proposed model can work with any level of abstractions exposed by the underlying network or the federated domains depending on their representation of resources.

A 5G network provides several service types, tailored to specific needs such as high bandwidth or low latency. On top of these communication services, verticals are enabled to deploy their own vertical services. These vertical service instances compete for the resources of the underlying common infrastructure. We present a resource arbitration approach that allows to handle such resource conflicts on a high level and to provide guidance to lower-level orchestration components.