Roberto Morabito

Hypervisors vs. Lightweight Virtualization: A Performance Comparison

Virtualization of operating systems provides a common way to run different services in the cloud. Recently, the lightweight virtualization technologies claim to offer superior performance. In this paper, we present a detailed performance comparison of traditional hypervisor based virtualization and new lightweight solutions. In our measurements, we use several benchmarks tools in order to understand the strengths, weaknesses, and anomalies introduced by these different platforms in terms of processing, storage, memory and network. Our results show that containers achieve generally better performance when compared with traditional virtual machines and other recent solutions. Albeit containers offer clearly more dense deployment of virtual machines, the performance difference with other technologies is in many cases relatively small.

OpenFlow over wireless networks: Performance analysis

Software Defined Networking (SDN) and OpenFlow represent the most commonly deployed approaches of the so called Programmable Networks. SDN is an emerging network architecture, which performs the subdivision of control plane and data plane and allows greater speed, greater scalability, and greater ductility in terms of routing and forwarding. OpenFlow, instead, is an SDN component that characterizes the communication between a controller and the devices within the SDN network. Although SDN and OpenFlow work efficiently in wired networks, the integration of these new paradigms over the wireless networks represents still and open issue. In fact, in a dense wireless scenario with an high number of base stations and a limited radio spectrum is still difficult to manage in a proper way operations such as radio spectrum allocation, interference management, handover management, and load balancing among the cells. In this paper, we present a performance analysis of the SDN and OpenFlow over wireless networks. The aim is to evaluate potential advantages introduced by the SDN architecture in terms of Quality of Service (QoS) metrics such as throughput, packet loss, end-to-end delay, and packet delivery ratio. An exhaustive simulation campaign has been conducted through the OMNeT++ network simulator framework by taking into account the new generation IP-based broadband wireless networks. The obtained results shown that the SDN architecture with OpenFlow introduces benefits in the network in term of resource management, transmission data-rate and end-to-end delay.

A performance evaluation of container technologies on Internet of Things devices

The use of virtualization technologies in different contexts - such as Cloud Environments, Internet of Things (IoT), Software Defined Networking (SDN) - has rapidly increased during the last years. Among these technologies, container-based solutions own characteristics for deploying distributed and lightweight applications. This paper presents a performance evaluation of container technologies on constrained devices, in this case, on Raspberry Pi. The study shows that, overall, the overhead added by containers is negligible.

Virtualization on Internet of Things Edge Devices With Container Technologies: A Performance Evaluation

Lightweight virtualization technologies have revolutionized the world of software development by introducing flexibility and innovation to this domain. Although the benefits introduced by these emerging solutions have been widely acknowledged in cloud computing, recent advances have led to the spread of such technologies in different contexts. As an example, the Internet of Things (IoT) and mobile edge computing benefit from container virtualization by exploiting the possibility of using these technologies not only in data centers but also on devices, which are characterized by fewer computational resources, such as single-board computers. This has led to a growing trend to more efficiently redesign the critical components of IoT/edge scenarios (e.g., gateways) to enable the concept of device virtualization. The possibility for efficiently deploying virtualized instances on single-board computers has already been addressed in recent studies; however, these studies considered only a limited number of devices and omitted important performance metrics from their empirical assessments. This paper seeks to fill this gap and to provide insights for future deployments through a comprehensive performance evaluation that aims to show the strengths and weaknesses of several low-power devices when handling container-virtualized instances.

The design of the gateway for the Cloud of Things

The increasing momentum of the Internet of Things (IoT) leaded to the development of a huge number of applications in different domains. Those applications are based on different standards and protocols, making therefore the IoT landscape widely fragmented. In this context, the evolution of Web semantic technologies together with the popularity of Cloud computing represents a solution to enable the horizontal integration of various IoT applications and platforms. This is what the Cloud of Things (CoT) aims to achieve. In this paper, we propose the design of a gateway for the Cloud of Things. The proposed gateway is able to manage semantic-like things and at the same time to act as an end-point for the presentation of data to users. Moreover, thanks to the use of virtualized software—which introduces a negligible impact in terms of performance—the gateway enables a lightweight and dense deployment of services. The paper describes the above technologies and how to combine them in order to design the gateway. Furthermore, we provide information about use cases, hardware, performance evaluation, and future hints to enhance the gateway.

Enabling Data Processing at the Network Edge through Lightweight Virtualization Technologies

Cloud computing plays a crucial role in making Internet of Things (IoT) becoming a central part of future industries, society and peoples life. However, the increase of the number of devices connected to the different networks, the huge amount of data produced by them, and the advanced requirements of many IoT applications, has resulted in new technical challenges. This has lead to the introduction of an edge-computing approach, which is intended to make the management of such networks more efficient. The paradigm aims to move part of the data processing operations close to the data sources. Such operations are performed by means of network entities - like IoT gateways or local servers - near the IoT device. In this paper, we describe the design of a multifunctional IoT gateway that, making use of lightweight virtualization technologies such as Docker containers, allows managing different services, including data processing services, so as to enable the migration towards the edge based approach. Furthermore, we show how the introduction of container-based technologies can bring several benefits without impacting the gateway performance.

Lightweight virtualization as enabling technology for future smart cars

Modern vehicles are equipped with several interconnected sensors on board for monitoring and diagnosis purposes; their availability is a main driver for the development of novel applications in the smart vehicle domain. In this paper, we propose a Docker container-based platform as solution for implementing customized smart car applications. Through a proof-of-concept prototype—developed on a Raspberry Pi3 board—we show that a container-based virtualization approach is not only viable but also effective and flexible in the management of several parallel processes running on On Board Unit. More specifically, the platform can take priority-based decisions by handling multiple inputs, e.g., data from the CANbus based on the OBD II codes, video from the on-board webcam, and so on. Results are promising for the development of future in-vehicle virtualized platforms.

Evaluating Performance of Containerized IoT Services for Clustered Devices at the Network Edge

The constant and fast increase in the number of heterogeneous Internet of Things (IoT) devices that populate everyday life environments brings new challenges to the full exploitation of the computation, memory, sensing, and actuation resources associated to them. In this context, device virtualization solutions and platforms may definitely play a key role in enabling the desired tradeoff between flexibility and performance. This paper focuses on lightweight virtualization technologies for IoT devices, suitably thought to effectively deploy new integrated applications and to create a novel distributed and virtualized ecosystem. Two different frameworks for container-based IoT service provisioning are compared, the one based on a direct interaction between two cooperating devices and the other based on the presence of a manager supervising the operations between cooperating devices forming a cluster. In the latter case, accounting for the growing impetus to move intelligence toward the edge of the network, management features are implemented at the network access point to provide short latency responses. We also introduce the outcomes of a thorough performance evaluation campaign conducted via a real IoT testbed. The measurements, performed by accounting for the constraints of typical IoT nodes, shed light on the actual feasibility of container-based IoT frameworks.

LEGIoT: A Lightweight Edge Gateway for the Internet of Things

Abstract The stringent latency together with the higher bandwidth requirements of current Internet of Things (IoT) applications, are leading to the definition of new network-infrastructures, such as Multi-access Edge Computing (MEC). This emerging paradigm encompasses the execution of many network tasks at the edge and in particular on constrained gateways that have also to deal with the plethora of disparate technologies available in the IoT landscape. To cope with these issues, we introduce a Lightweight Edge Gateway for the Internet of Things (LEGIoT) architecture. It relies on the modular characteristic of microservices and the flexibility of lightweight virtualization technologies to guarantee an extensible and flexible solution. In particular, by combining the implementation of specific frameworks and the benefits of container-based virtualization, our proposal enhances the suitability of edge gateways towards a wide variety of IoT protocols/applications (for both downlink and uplink) enabling an optimized resource management and taking into account requirements such as energy efficiency, multi-tenancy, and interoperability. LEGIoT is designed to be hardware agnostic and its implementation has been tested within a real sensor network. Achieved results demonstrate its scalability and suitability to host different applications meant to provide a wide range of IoT services.

Enabling a lightweight Edge Gateway-as-a-Service for the Internet of Things

Since its introduction, the Internet of Things (IoT) has changed several aspects of our lives, leading to the commercialization of different heterogeneous devices. In order to bridge the gap among these heterogeneous devices, in some of the most common IoT use cases-e.g., smart home, smart buildings, etc.- the presence of a gateway as an enabler of interoperability is required. In this paper, we introduce the concept of a Gateway-as-a-Service (GaaS), a lightweight device that can be shared between different users thanks to the use of virtualization techniques. Performance has been evaluated on real hardware and results demonstrate the lightweight characteristics of the proposal.