Danilo Amendola

Distributed and adaptive resource management in Cloud-assisted Cognitive Radio Vehicular Networks with hard reliability guarantees

Abstract In this contribution, we design and test the performance of a distributed and adaptive resource management controller, which allows the optimal exploitation of Cognitive Radio and soft-input/soft-output data fusion in Vehicular Access Networks. The ultimate goal is to allow energy and computing-limited car smartphones to utilize the available Vehicular-to-Infrastructure WiFi connections for performing traffic offloading towards local or remote Clouds by opportunistically acceding to a spectral-limited wireless backbone built up by multiple Roadside Units. For this purpose, we recast the afforded resource management problem into a suitable constrained stochastic Network Utility Maximization problem. Afterwards, we derive the optimal cognitive resource management controller, which dynamically allocates the access time-windows at the serving Roadside Units (i.e., the access points) together with the access rates and traffic flows at the served Vehicular Clients (i.e., the secondary users of the wireless backbone). Interestingly, the developed controller provides hard reliability guarantees to the Cloud Service Provider (i.e., the primary user of the wireless backbone) on a per-slot basis. Furthermore, it is also capable to self-acquire context information about the currently available bandwidth-energy resources, so as to quickly adapt to the mobility-induced abrupt changes of the state of the vehicular network, even in the presence of fadings , imperfect context information and intermittent Vehicular-to-Infrastructure connectivity. Finally, we develop a related access protocol, which supports a fully distributed and scalable implementation of the optimal controller.

Energy-saving adaptive computing and traffic engineering for real-time-service data centers

In this paper, we propose a traffic engineering-based adaptive approach to dynamically reconfigure the computing-plus-communication resources of networked data centers which support in real-time the service requirements of mobile clients connected by TCP/IP energy-limited wireless backbones. The goal is to maximize the energy-efficiency, while meeting hard QoS requirements on the delivered transmission rate and processing delay. In order to cope with the (possibly, unpredictable) fluctuations of the offered workload, the proposed optimal cross-layer resource controller is adaptive. It jointly performs: i) the balanced control and dispatching of the admitted workload; ii) the dynamic reconfiguration of the Virtual Machines (VMs) instantiated onto the parallel computing platform at the data center; and iii) the rate control of the traffic injected into the wireless backbone for delivering the service to the requiring clients. Our experimental results show that the proposed technique improves energy consumption of servers by 25% compared to state of the art improvement on average in the entire data center.

Energy-efficient adaptive networked datacenters for the QoS support of real-time applications

In this paper, we develop the optimal minimum-energy scheduler for the adaptive joint allocation of the task sizes, computing rates, communication rates and communication powers in virtualized networked data centers (VNetDCs) that operate under hard per-job delay-constraints. The considered VNetDC platform works at the Middleware layer of the underlying protocol stack. It aims at supporting real-time stream service (such as, for example, the emerging big data stream computing (BDSC) services) by adopting the software-as-a-service (SaaS) computing model. Our objective is the minimization of the overall computing-plus-communication energy consumption. The main new contributions of the paper are the following ones: (i) the computing-plus-communication resources are jointly allotted in an adaptive fashion by accounting in real-time for both the (possibly, unpredictable) time fluctuations of the offered workload and the reconfiguration costs of the considered VNetDC platform; (ii) hard per-job delay-constraints on the overall allowed computing-plus-communication latencies are enforced; and, (iii) to deal with the inherently nonconvex nature of the resulting resource optimization problem, a novel solving approach is developed, that leads to the lossless decomposition of the afforded problem into the cascade of two simpler sub-problems. The sensitivity of the energy consumption of the proposed scheduler on the allowed processing latency, as well as the peak-to-mean ratio (PMR) and the correlation coefficient (i.e., the smoothness) of the offered workload is numerically tested under both synthetically generated and real-world workload traces. Finally, as an index of the attained energy efficiency, we compare the energy consumption of the proposed scheduler with the corresponding ones of some benchmark static, hybrid and sequential schedulers and numerically evaluate the resulting percent energy gaps.

Reliable Adaptive Resource Management for Cognitive Cloud Vehicular Networks

In this paper, we design and test the performance of a distributed and adaptive resource management controller, which allows the optimal exploitation of cognitive radio and soft-input/soft-output data fusion in vehicular access networks. The goal is to allow energy and computing-limited car smartphones to utilize the available vehicle-to-infrastructure (V2I) WiFi connections for performing traffic offloading toward local or remote clouds by opportunistically acceding to a spectral-limited wireless backbone built up by multiple roadside units (i.e., cloudlets). We cast the resource management problem into a suitable constrained stochastic network utility maximization problem and derive the optimal cognitive resource manager that dynamically allocates the access time windows at the serving roadside units (i.e., the access points), together with the access rates and traffic flows at the served vehicular clients (i.e., the secondary users of the wireless backbone). The developed controller provides hard reliability guarantees to the cloud service provider (i.e., the primary user of the wireless backbone) on a per-slot basis. Furthermore, it is able to acquire context information about the currently available bandwidth-energy resources to quickly adapt to the mobility-induced abrupt changes in the state of the vehicular network.

Bandwidth Management VMs Live Migration in Wireless Fog Computing for 5G Networks

Live virtual machine migration aims at enabling the dynamic balanced use of the networking/computing physical resources of virtualized data-centers, so to lead to reduced energy consumption. Here, we analytically characterize, prototype in software and test an optimal bandwidth manager for live migration of VMs in wireless channel. In this paper we present the optimal tunable-complexity bandwidth manager (TCBM) for the QoS live migration of VMs under a wireless channel from smartphone to access point. The goal is the minimization of the migration-induced communication energy under service level agreement (SLA)-induced hard constrains on the total migration time, downtime and overall available bandwidth.

Minimum-energy bandwidth management for QoS live migration of virtual machines

Live virtual machine (VM) migration aims at enabling the dynamic balanced use of the networking/computing physical resources of virtualized datacenters, so to lead to reduced energy consumption. However, the bandwidth consumption and latency of current state-of-the-art live VM migration techniques still reduce the experienced benefits to much less than their potential. Motivated by this consideration, in this paper, we analytically characterize, prototype in software and test through field trials the optimal bandwidth manager for intra-datacenter live migration of VMs. The goal is the minimization of the migration-induced communication energy under service level agreement (SLA)-induced hard constraints on the total migration time, downtime, slowdown of the migrating applications and overall available bandwidth. For this purpose, after recognizing that the resulting (nonconvex) optimization problem is an instance of Geometric Programming, we solve it by resorting to suitably developed adaptive version of the so-called primal-dual gradient-based iterations and, then, we analytically characterize its feasibility conditions. Hence, we prototype the resulting bandwidth manager atop an intra-datacenter wired test-bed, and, then, test and compare its energy performance through extensive field trials. The carried out field trials point out that: (i) the energy savings attained by the proposed bandwidth manager over the state-of-the-art ones currently utilized by Xen, KVM and VMware hypervisors are over 40% and approach 66% under strict QoS constraints; (ii) the proposed bandwidth manager is capable to quickly adapt to the abrupt changes possibly experienced by the dirty rates of the running applications and/or the round trip times of the utilized (possibly, congested) TCP/IP connections; and, (iii) its actual implementation may be carried out in a distributed and scalable way, and it consumes less than 1.5% of the CPU computing power per migrated VM.

Efficient Neighbor Discovery in RFID based devices over resource-constrained DTN networks

In this paper we consider Delay Tolerant Network (DTN) as a technology to implement a future network in a People Centric Networking paradigm, using Active RFID carried by people that exchange information with each other. We propose a novel and real Neighbor Discovery (ND) phase on active RFID based DTN using Open Beacon devices. In particular, we propose a solution using the Sift distribution on a probabilistic persistent approach called Sift-Persistent. We simulated P-Persistent, Aloha and our solution using our customized Java simulator. We implemented Sift-Persistent and P-Persistent on Open-Beacon devices, comparing the simulation results and test-beds. Moreover, simulations and real testbed show a coherent behavior validating our proposal in the RFID context. Performance evaluations have been tested in terms of discovered neighbors.

Performance evaluation of primary-secondary reliable resource-management in vehicular networks

We design and test a distributed and adaptive resource management controller in Vehicular Access Networks, allowing energy and computing-limited car smart phones to opportunistically accede to a spectral-limited wireless backbone. We cast the resource management problem into a suitable constrained stochastic Network Utility Maximization problem and derive the optimal cognitive resource management controller, which dynamically allocates the access time-windows at the serving Roadside Units (i.e., the primary users) and the access rates and traffic flows at the served Vehicular Clients (i.e., the secondary users), allowing hard reliability guarantees to Roadside Units. We validated the controller performances in real-word application scenarios.

Resource-Management for Vehicular Real-Time Application under Hard Reliability Constraints

In this paper, we design and test a full distributed and scalable resource-management scheduler for Vehicular Real-Time applications. We dynamically allocate the access time window (at the RoadSide Units) and the access rate and traffic flows (at the Vehicular Clients) under hard reliability collision constraints. We provide the optimal memoryless scheduler for network utility maximization, showing as it presents no loss in the network average utility with respect to not real-time soft reliability schedulers. Finally, the proposed scheduler exploits an ad-hoc designed soft-input/soft-output data fusion algorithm, able to supply in real-time reliable context-information, even in the presence of fading-affected and intermittent vehicular-to-infrastructure connectivity.

Neighbor discovery in delay tolerant networking using resource-constraint devices

In delay tolerant networking (DTN) nodes exploit their mobility in order to carry messages to their intended destination. Thus the knowledge of a nodes neighbors over time, is a fundamental requirement for DTN nodes to exchange knowledge and messages. A typical problem in this task occurs when the neighboring nodes try to response to the neighbor discovery request initiated by a requesting node, during a fixed contention time window. In this paper a novel neighbor discovery protocol proposed for resource constraint devices (RFID tags) running according to the delay tolerant networking paradigm. The proposed protocol is based on the traditional P-Persistent CSMA algorithm, but with the addition of the sift-distribution (sift-Persistent) in order to reduce the collisions during the response phase. The proposal has been tested both in a simulator and in a real testbed under the OpenBeacon framework. Moreover, simulations and real testbed show a coherent behavior validating our proposal in the RFID context. Performance evaluations have been tested in terms of discovered neighbors.