From 2021 to 2028, the worldwide telecom services industry will increase at a compound growth rate of 5.4%. By 2025, the market for Telecom Equipment is expected to develop at a rate of 11.23%. One of the main aspects fuelling this market is an increased investment in 5G infrastructure deployment due to a shift in customer preference for next-generation technologies and smartphone devices. Increased need for value-added managed services, a growing number of mobile users, and surging demand for high-speed data connectivity are all major market drivers. Over the last few decades, the global communication network has clearly been one of the most important areas for continuing technical advancement.

The expansion of Fiber-To-The-Home (FTTH) networks creates high costs due to expensive excavation procedures. Optimizing the planning process and minimizing the cost of the earth excavation work therefore lead to large savings. Mathematically, the FTTH network problem can be described as a minimum Steiner Tree problem. Even though the Steiner Tree problem has already been investigated intensively in the last decades, it might be further optimized with the help of new computing paradigms and emerging approaches. This work studies upcoming technologies, such as Quantum Annealing, Simulated Annealing and nature-inspired methods like Evolutionary Algorithms or slime-mold-based optimization. Additionally, we investigate partitioning and simplifying methods. Evaluated on several real-life problem instances, we could outperform a traditional, widely-used baseline (NetworkX Approximate Solver) on most of the domains. Prior partitioning of the initial graph and the presented slime-mold-based approach were especially valuable for a cost-efficient approximation. Quantum Annealing seems promising, but was limited by the number of available qubits.

Creating a programmable software infrastructure for telecommunication operations promises to reduce both the capital expenditure (CAPEX) and the operational expenses (OPEX) of the 5G telecommunications operators. What is exciting to many of us who work in this space is that the convergence of telecommunications, the cloud, and edge infrastructures will open up opportunities for new innovations and revenue for both the telecommunications industry and the cloud ecosystem. In this blog, we focus on video, the dominant traffic type on the internet since the introduction of 4G networks. With 5G, not only will the volume of video traffic increase, but there will also be many new solutions for industries, from retail to manufacturing to healthcare and forest monitoring, infusing deep learning and AI for video analytics scenarios. The symbiotic evolution of video analytics and edge computing provides opportunities for operators to offer new services which they can monetize with their customers.

Scheduling decisions in parallel queuing systems arise as a fundamental problem, underlying the dimensioning and operation of many computing and communication systems, such as job routing in data center clusters, multipath communication, and Big Data systems. In essence, the scheduler maps each arriving job to one of the possibly heterogeneous servers while aiming at an optimization goal such as load balancing, low average delay or low loss rate. One main difficulty in finding optimal scheduling decisions here is that the scheduler only partially observes the impact of its decisions, e.g., through the delayed acknowledgements of the served jobs. In this paper, we provide a partially observable (PO) model that captures the scheduling decisions in parallel queuing systems under limited information of delayed acknowledgements. We present a simulation model for this PO system to find a near-optimal scheduling policy in real-time using a scalable Monte Carlo tree search algorithm. We numerically show that the resulting policy outperforms other limited information scheduling strategies such as variants of Join-the-Most-Observations and has comparable performance to full information strategies like: Join-the-Shortest-Queue, Join-the- Shortest-Queue(d) and Shortest-Expected-Delay. Finally, we show how our approach can optimise the real-time parallel processing by using network data provided by Kaggle.

Cloud networks are difficult to monitor because they grow rapidly and the budgets for monitoring them are limited. We propose a framework for estimating network metrics, such as latency and packet loss, with guarantees on estimation errors for a fixed monitoring budget. Our proposed algorithms produce a distribution of probes across network paths, which we then monitor; and are based on A- and E-optimal experimental designs in statistics. Unfortunately, these designs are too computationally costly to use at production scale. We propose their scalable and near-optimal approximations based on the Frank-Wolfe algorithm. We validate our approaches in simulation on real network topologies, and also using a production probing system in a real cloud network. We show major gains in reducing the probing budget compared to both production and academic baselines, while maintaining low estimation errors, even with very low probing budgets.

Recent years have seen the vast potential of Graph Neural Networks (GNN) in many fields where data is structured as graphs (e.g., chemistry, recommender systems). In particular, GNNs are becoming increasingly popular in the field of networking, as graphs are intrinsically present at many levels (e.g., topology, routing). The main novelty of GNNs is their ability to generalize to other networks unseen during training, which is an essential feature for developing practical Machine Learning (ML) solutions for networking. However, implementing a functional GNN prototype is currently a cumbersome task that requires strong skills in neural network programming. This poses an important barrier to network engineers that often do not have the necessary ML expertise. In this article, we present IGNNITION, a novel open-source framework that enables fast prototyping of GNNs for networking systems. IGNNITION is based on an intuitive high-level abstraction that hides the complexity behind GNNs, while still offering great flexibility to build custom GNN architectures. To showcase the versatility and performance of this framework, we implement two state-of-the-art GNN models applied to different networking use cases. Our results show that the GNN models produced by IGNNITION are equivalent in terms of accuracy and performance to their native implementations in TensorFlow.

This paper investigates an unmanned aerial vehicle (UAV)-assisted wireless powered mobile-edge computing (MEC) system, where the UAV powers the mobile terminals by wireless power transfer (WPT) and provides computation service for them. We aim to maximize the computation rate of terminals while ensuring fairness among them. Considering the random trajectories of mobile terminals, we propose a soft actor-critic (SAC)-based UAV trajectory planning and resource allocation (SAC-TR) algorithm, which combines off-policy and maximum entropy reinforcement learning to promote the convergence of the algorithm. We design the reward as a heterogeneous function of computation rate, fairness, and reaching of destination. Simulation results show that SAC-TR can quickly adapt to varying network environments and outperform representative benchmarks in a variety of situations.

Emergency personnel respond to various situations ranging from fire, medical, hazardous materials, industrial accidents, to natural disasters. Situations such as natural disasters or terrorist acts require a multifaceted response of firefighters, paramedics, hazmat teams, and other agencies. Engineering AI systems that aid emergency personnel proves to be a difficult system engineering problem. Mission-critical "edge AI" situations require low-latency, reliable analytics. To further add complexity, a high degree of model accuracy is required when lives are at stake, creating a need for the deployment of highly accurate, however computationally intensive models to resource-constrained devices. To address all these issues, we propose an agent-based architecture for deployment of AI agents via 5G service-based architecture.

What do you get when you combine 5G and AI with advanced drone development? One answer is from Qualcomm's recent launch of its Flight RB5 5G Platform, a reference drone containing computing at lower power with AI, 5G, and long-range Wi-Fi 6 connectivity. According to the company in a press release, the drone and reference design contains "enhanced autonomy and intelligence features" powered by the Qualcomm QRB5165 processor. Announced in June 2020, the QRB5165 processor is customized for robotics applications and is coupled with the Qualcomm AI Engine, which delivers 15 trillion operations per second (Tops) of AI performance. This allows it to run complex AI and deep learning workloads, and on-device machine learning and accurate edge inferencing while using lower power, according to a Qualcomm product description.

Domestic surveillance programs may be in for an AI upgrade. The National Security Agency of the United States just awarded a $2 billion contract to Hewlett Packard Enterprise to develop high-performance computing power that the agency will use to reach its data analytics and artificial intelligence needs, according to a Wednesday statement from the company. However, it's important to keep in mind that the NSA has repeatedly pushed for access to private information from telecommunications companies and internet servers, which could mean a major upgrade is in store for the surveillance of ordinary people. During the course of the 10-year contract, the NSA will pay to employ HSE's computing technology, which will also build a new platform that will blend the company's ProLiant servers with its Apollo data storage system. Combined, the new system will "ingest and process high volumes of data, and support deep learning and artificial intelligence capabilities," read the company press release.