- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Software System Performance and Reliability
- Software-Defined Networks and 5G
- Caching and Content Delivery
- Blockchain Technology Applications and Security
- Network Security and Intrusion Detection
- IoT Networks and Protocols
- Transportation and Mobility Innovations
- Energy Efficient Wireless Sensor Networks
- Network Traffic and Congestion Control
- Energy Efficiency and Management
- Internet Traffic Analysis and Secure E-voting
- Smart Grid Energy Management
- Advanced Neural Network Applications
- Mobile Agent-Based Network Management
- Service-Oriented Architecture and Web Services
- Energy Load and Power Forecasting
- Age of Information Optimization
- CCD and CMOS Imaging Sensors
- Cognitive Computing and Networks
- Recommender Systems and Techniques
- Cooperative Communication and Network Coding
- Context-Aware Activity Recognition Systems
- Cloud Data Security Solutions
Fondazione Bruno Kessler
2011-2024
Center for Research and Telecommunication Experimentation for Networked Communities
2016-2017
In this paper we present Foggy, an architectural framework and software platform based on Open Source technologies. Foggy orchestrates application workload, negotiates resources supports IoT operations for multi-tier, distributed, heterogeneous decentralized Cloud Computing systems. is tailored emerging domains such as 5G Networks IoT, which demand services to be distributed located close data sources users following the Fog paradigm. provides a infrastructure owners tenants (i.e.,...
Fog computing promises to extend cloud match emerging demands for low latency, location-awareness and dynamic computation. It thus brings data processing close the edge of network by leveraging on devices with different computational characteristics. However, heterogeneity, geographical distribution, data-intensive profiles IoT deployments render placement fog applications a fundamental problem guarantee target performance figures. This is core challenge providers offer infrastructure as...
Multi-cloud environments enable a cost-efficient scaling of cloud-native applications across geographically distributed virtual nodes with different pricing models. In this context, the resource fragmentation caused by frequent changes in demands deployed microservices, along allocation or termination new and existing increases deployment cost. Therefore, re-orchestrating microservices on cheaper configuration multi-cloud offers practical solution to restore cost efficiency deployment....
Fog computing extends cloud technology to the edge of infrastructure support dynamic computation for IoT applications. Reduced latency and location awareness in objects' data access is attained by displacing workloads from central devices. Doing so, it reduces raw transfers target objects cloud, thus overcoming communication bottlenecks. This a key step towards pervasive uptake next generation IoT-based services. In this work we study efficient orchestration applications fog computing, where...
We introduce Cloud4IoT, a platform offering automatic deployment, orchestration and dynamic configuration of IoT support software components data-intensive applications for data processing analytics, thus enabling plug-and-play integration new sensor objects workload scalability. Cloud4IoT enables the concept Infrastructure as Code in context: it empowers operations with flexibility elasticity Cloud services. Furthermore shifts traditionally centralized architectures towards more distributed...
This demonstration aims at showcasing an initial version of the DECENTER Brokerage Platform, which leverages Ethereum blockchain to enable resource federation among different Fog Computing infrastructures. We consider a scenario where Italian Infrastructure Provider wants seamlessly extend its pool resources get access IP camera located in Korea, so that it can deploy application locally perform text recognition from live video stream.
Multi-cloud systems facilitate a cost-efficient and geographically-distributed deployment of microservice-based ap-plications by temporary leasing virtual nodes with diverse pricing models. To preserve the cost-efficiency multi -cloud deploy-ments' it is essential to redeploy microservices onto available according dynamic resource configuration, which often performed better accommodate workload variations. However, this approach leads frequent service disruption since applications are...
This demonstration aims at showcasing an application of a cluster federation to increase the elasticity and resilience Fog Computing system. Federation is performed by means Kubernetes Cluster (KubeFed), framework we augmented with two-phase workload placement mechanism that smartly distributes applications' microservices among federated infrastructure. Despite KubeFed has been generally used in multi-cloud environment for workloads split on different cloud providers avoiding lock-in, this...
Nowadays IoT applications consist of a collection loosely coupled modules, namely microservices, that can be managed and placed in heterogeneous environment consisting private public resources. It follows distributing the application logic introduces new challenges guaranteeing performance reducing costs. However, most existing solutions are focused on pay-per-use costs without considering microservice-based architecture. We propose cost-effective workload allocation for applications. model...
Multi-cloud systems facilitate a cost-efficient and geographically-distributed deployment of microservice-based applications by temporary leasing virtual nodes with diverse pricing models. To preserve the cost-efficiency multi-cloud deployments, it is essential to redeploy microservices onto available according dynamic resource configuration, which often performed better accommodate workload variations. However, this approach leads frequent service disruption since are continuously shutdown...
The migration of software applications to the public cloud unlocks a number advantages, such as flexibility and elasticity, that can be tampered by an inappropriate inefficient usage computational resources producing uncontrollable Operational Expenses. In this work we experiment with cost-aware rescheduling algorithm show how its integration Kubernetes in hybrid environment yield relevant advantages terms cost savings.
We (devise and) demonstrate the benefits of a methodology and toolset for orchestrating Cloud-native applications to balance minimization risks due presence security threats achievement service performance requirements - expressed on, e.g., computational resources, network throughput latency. The demo proves effectiveness in set microservices implementing prominent Cooperative, Connected Automated Mobility (CCAM) service.
The area of AI application continues to grow from resource-rich environment such as cloud resource-constraint embedded devices. However, management on the device is still a challenging task due different other that This paper proposes an platform for cluster which consists edge devices and resources. proposed system provides efficient methods identify hardware acceleration resources resource specific application. implementation VMs are described presented.
The remarkable success of cloud computing has change the way services and applications are implemented offered not least because flexibility scalability that such an environment can offer. Cloud federation tremendous potential for industry as effective to increase c
Fog computing extends cloud technology to the edge of infrastructure let IoT applications access objects' data with reduced latency, location awareness and dynamic computation. By displacing workloads from central devices, fog overcomes communication bottlenecks avoiding raw transfer cloud, thus paving way for next generation IoT-based applications. In this paper we study scheduling placement in computing, which is key ensure profitability involved stakeholders. We consider a scenario where...
In network security, Network Function Virtualization can be exploited to implement flexible security services tailored specific user needs. However, in practice this is hard achieve due the limitations of reference software platforms, such as Kubernetes, which are designed orchestrate cloud-native services. work, we complement Kubernetes with a state-of-the-art algorithm for application-aware provisioning We demonstrate that proposed solution improves basic mechanisms, default scheduler,...