Papers by Enzo Baccarelli
The Journal of Supercomputing
Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks ... more Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks (CycleGANs) are two emerging machine learning models that, up to now, have been used as generative models, i.e., to generate output data sampled from a target probability distribution. However, these models are also equipped with encoding modules, which, after weakly supervised training, could be, in principle, exploited for the extraction of hidden features from the input data. At the present time, how these extracted features could be effectively exploited for classification tasks is still an unexplored field. Hence, motivated by this consideration, in this paper, we develop and numerically test the performance of a novel inference engine that relies on the exploitation of BiGAN and CycleGAN-learned hidden features for the detection of COVID-19 disease from other lung diseases in computer tomography (CT) scans. In this respect, the main contributions of the paper are twofold. First, we...
Applied Sciences, 2021
The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early ... more The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early exits, executed atop virtualized multi-tier Fog platforms, makes feasible the real-time and energy-efficient execution of analytics required by future Internet applications. However, until now, toolkits for the evaluation of energy-vs.-delay performance of the inference phase of CDNNs executed on such platforms, have not been available. Motivated by these considerations, in this contribution, we present DeepFogSim. It is a MATLAB-supported software toolbox aiming at testing the performance of virtualized technological platforms for the real-time distributed execution of the inference phase of CDNNs with early exits under IoT realms. The main peculiar features of the proposed DeepFogSim toolbox are that: (i) it allows the joint dynamic energy-aware optimization of the Fog-hosted computing-networking resources under hard constraints on the tolerated inference delays; (ii) it allows the rep...
Applied Sciences, 2021
The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researc... more The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures ...
Computation, 2021
In parallel with the vast medical research on clinical treatment of COVID-19, an important action... more In parallel with the vast medical research on clinical treatment of COVID-19, an important action to have the disease completely under control is to carefully monitor the patients. What the detection of COVID-19 relies on most is the viral tests, however, the study of X-rays is helpful due to the ease of availability. There are various studies that employ Deep Learning (DL) paradigms, aiming at reinforcing the radiography-based recognition of lung infection by COVID-19. In this regard, we make a comparison of the noteworthy approaches devoted to the binary classification of infected images by using DL techniques, then we also propose a variant of a convolutional neural network (CNN) with optimized parameters, which performs very well on a recent dataset of COVID-19. The proposed model’s effectiveness is demonstrated to be of considerable importance due to its uncomplicated design, in contrast to other presented models. In our approach, we randomly put several images of the utilized ...
Applied Sciences, 2019
It is expected that the pervasive deployment of multi-tier 5G-supported Mobile-Fog-Cloudtechnolog... more It is expected that the pervasive deployment of multi-tier 5G-supported Mobile-Fog-Cloudtechnological computing platforms will constitute an effective means to support the real-time execution of future Internet applications by resource- and energy-limited mobile devices. Increasing interest in this emerging networking-computing technology demands the optimization and performance evaluation of several parts of the underlying infrastructures. However, field trials are challenging due to their operational costs, and in every case, the obtained results could be difficult to repeat and customize. These emerging Mobile-Fog-Cloud ecosystems still lack, indeed, customizable software tools for the performance simulation of their computing-networking building blocks. Motivated by these considerations, in this contribution, we present VirtFogSim. It is a MATLAB-supported software toolbox that allows the dynamic joint optimization and tracking of the energy and delay performance of Mobile-Fog-C...
Applied Sciences, 2019
In this paper, we characterize the main building blocks and numerically verify the classification... more In this paper, we characterize the main building blocks and numerically verify the classification accuracy and energy performance of SmartFog, a distributed and virtualized networked Fog technological platform for the support for Stacked Denoising Auto-Encoder (SDAE)-based anomaly detection in data flows generated by Smart-Meters (SMs). In SmartFog, the various layers of an SDAE are pretrained at different Fog nodes, in order to distribute the overall computational efforts and, then, save energy. For this purpose, a new Adaptive Elitist Genetic Algorithm (AEGA) is “ad hoc” designed to find the optimized allocation of the SDAE layers to the Fog nodes. Interestingly, the proposed AEGA implements a (novel) mechanism that adaptively tunes the exploration and exploitation capabilities of the AEGA, in order to quickly escape the attraction basins of local minima of the underlying energy objective function and, then, speed up the convergence towards global minima. As a matter of fact, the ...
The Journal of Supercomputing, 2018
In this paper, we explore on a comparative basis the performance suitability of meta-heuristic, s... more In this paper, we explore on a comparative basis the performance suitability of meta-heuristic, sometime denoted as random search algorithms, and greedy-type heuristics for the energy-saving joint dynamic scaling and consolidation of the network-plus-computing resources hosted by networked virtualized data centers when the target is the support of real-time streaming-type applications. For this purpose, the energy and delay performances of Tabu Search (TS), Simulated Annealing (SA) and Evolutionary Strategy (ES) meta-heuristics are tested and compared with the corresponding ones of Best-Fit Decreasing-type heuristics, in order to give insight on the resulting performance-versus-implementation complexity trade-offs. In principle, the considered meta-heuristics and heuristics are general formal approaches that can be applied to large classes of (typically, non-convex and mixed integer) optimization problems. However, specially for the meta-heuristics, a main challenge is to design them to properly address the real-time joint computing-plus-networking resource consolidation and scaling optimization problem. To this purpose, the aim of this paper is: (i) introduce a novel Virtual Machine Allocation (VMA) scheme that aims at choosing a suitable set of possible Virtual Machine placements among the (possibly, non-homogeneous) set of available servers; (ii) propose a new class of random B Michele Scarpiniti
The Journal of Supercomputing, 2018
With the incoming 5G access networks, it is forecasted that Fog computing (FC) and Internet of Th... more With the incoming 5G access networks, it is forecasted that Fog computing (FC) and Internet of Things (IoT) will converge onto the Fog-of-IoT paradigm. Since the FC paradigm spreads, by design, networking and computing resources over the wireless access network, it would enable the support of computing-intensive and delay-sensitive streaming applications under the energy-limited wireless IoT realm. Motivated by this consideration, the goal of this paper is threefold. First, it provides a motivating study the main "killer" application areas envisioned for the considered Fog-of-IoT paradigm. Second, it presents the design of a CoNtainer-based virtualized networked computing architecture. The proposed architecture operates at the Middleware layer and exploits the native capability of the Container Engines, so as to allow the dynamic real-time scaling of the available computing-plus-networking virtualized resources. Third, the paper presents a low-complexity penalty-aware bin packing-type heuristic for the dynamic management of the resulting virtualized computing-plusnetworking resources. The proposed heuristic pursues the joint minimization of the networking-plus-computing energy by adaptively scaling up/down the processing speeds of the virtual processors and transport throughputs of the instantiated TCP/IP virtual connections, while guaranteeing hard (i.e., deterministic) upper bounds on the per-task computing-plus-networking delays. Finally, the actual energy performanceversus-implementation complexity trade-off of the proposed resource manager is
Computer Communications, 2017
The emerging utilization of Software-as-a-Service (SaaS) Fog computing centers as an Internet vir... more The emerging utilization of Software-as-a-Service (SaaS) Fog computing centers as an Internet virtual computing commodity is raising concerns over the energy consumptions of networked data centers for the support of delay-sensitive applications. In addition to the energy consumed by the servers, the energy wasted by the network devices that support TCP/IP reliable inter-Virtual Machines (VMs) connections is becoming a significant challenge. In this paper, we propose and develop a framework for the joint characterization and optimization of TCP/IP SaaS Fog data centers that utilize a bank of queues for increasing the fraction of the admitted workload. Our goal is twofold: (i) we maximize the average workload admitted by the data center; and, (ii) we minimize the resulting networking-plus-computing average energy consumption. For this purpose, we exploit the Lyapunov stochastic optimization approach, in order to design and analyze an optimal (yet practical) online joint resource management framework, which dynamically performs: (i) admission control; (ii) dispatching of the admitted workload; (iii) flow control of the inter-VM TCP/IP connections; (iv) queue control; (v) up/down scaling of the processing frequencies of the instantiated VMs; and, (vi) adaptive joint consolidation of both physical servers and TCP/IP connections. The salient features of the resulting scheduler (e.g., the Q * scheduler) are that: (i) it admits distributed and scalable implementation; (ii) it provides deterministic bounds on the instantaneous queue backlogs; (iii) it avoids queue overflow phenomena; and, (iv) it effectively tracks the (possibly unpredictable) time-fluctuations of the input workload, in order to perform joint resource consolidation without requiring any a priori information and/or forecast of the input workload. Actual energy and delay performances of the proposed scheduler are numerically evaluated and compared against the corresponding ones of some competing and state-of-the-art schedulers, under: (i) Fast-Giga-10Giga Ethernet switching technologies; (ii) various settings of the reconfiguration-consolidation costs; and, (iii) synthetic, as well as realworld workloads. The experimental results support the conclusion that the proposed scheduler can achieve over 30 percent energy savings.
2016 5th IEEE International Conference on Cloud Networking (Cloudnet), 2016
Live virtual machine migration aims at enabling the dynamic balanced use of the networking/comput... more 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.
2016 IEEE Symposium on Computers and Communication (ISCC), 2016
In this paper, we propose a dynamic resource provisioning scheduler to maximize the application t... more In this paper, we propose a dynamic resource provisioning scheduler to maximize the application throughput and minimize the computing-plus-communication energy consumption in virtualized networked data centers. The goal is to maximize the energy-efficiency, while meeting hard QoS requirements on processing delay. The resulting optimal resource scheduler is adaptive, and jointly performs: i) admission control of the input traffic offered by the cloud provider; ii) adaptive balanced control and dispatching of the admitted traffic; iii) dynamic reconfiguration and consolidation of the Dynamic Voltage and Frequency Scaling (DVFS)-enabled virtual machines instantiated onto the virtualized data center. The proposed scheduler can manage changes of the workload without requiring server estimation and prediction of its future trend. Furthermore, it takes into account the most advanced mechanisms for power reduction in servers, such as DVFS and reduced power states. Performance of the proposed scheduler is numerically tested and compared against the corresponding ones of some state-of-theart schedulers, under both synthetically generated and measured real-world workload traces. The results confirm the delay-vs.energy good performance of the proposed scheduler.
2015 IEEE Globecom Workshops (GC Wkshps), 2015
The expected pervasive use of mobile cloud computing and the growing number of Internet data cent... more The expected pervasive use of mobile cloud computing and the growing number of Internet data centers have brought forth many concerns, such as, energy costs and energy saving management of both data centers and mobile connections. Therefore, the need for adaptive and distributed resource allocation schedulers for minimizing the communication-plus-computing energy consumption has become increasingly important. In this paper, we propose and test an efficient dynamic resource provisioning scheduler that jointly minimizes computation and communication energy consumption, while guaranteeing user Quality of Service (QoS) constraints. We evaluate the performance of the proposed dynamic resource provisioning algorithm with respect to the execution time, goodput and bandwidth usage and compare the performance of the proposed scheduler against the exiting approaches. The attained experimental results show that the proposed dynamic resource provisioning algorithm achieves much higher energy-saving than the traditional schemes.
Advances in Systems Analysis, Software Engineering, and High Performance Computing
In this chapter, the authors develop the scheduler which optimizes the energy-vs.-performance tra... more In this chapter, the authors develop the scheduler which optimizes the energy-vs.-performance trade-off in Software-as-a-Service (SaaS) Virtualized Networked Data Centers (VNetDCs) that support real-time Big Data Stream Computing (BDSC) services. The objective is to minimize the communication-plus-computing energy which is wasted by processing streams of Big Data under hard real-time constrains on the per-job computing-plus-communication delays. In order to deal with the inherently nonconvex nature of the resulting resource management optimization problem, the authors develop a solving approach that leads to the lossless decomposition of the afforded problem into the cascade of two simpler sub-problems. The resulting optimal scheduler is amenable of scalable and distributed adaptive implementation. The performance of a Xen-based prototype of the scheduler is tested under several Big Data workload traces and compared with the corresponding ones of some state-of-the-art static and seq...
Vehicular Communications, 2015
ABSTRACT In this contribution, we design and test the performance of a distributed and adaptive r... more 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.
Proceedings of the fourth ACM international symposium on Development and analysis of intelligent vehicular networks and applications, 2014
ABSTRACT In this paper, a primary-secondary resource-management controller on Vehicular Networks ... more ABSTRACT In this paper, a primary-secondary resource-management controller on Vehicular Networks is designed and tested. 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 primary users (the serving Roadside Units) and the access rates and traffic flows at the secondary users (the served Vehicular Clients). We provide the optimal memoryless controllers under hard and soft primary-secondary collision constraints, showing as the hard controller presents no optimality gap in the average utility with respect to the soft one. Finally we generalize the framework integrating the controllers with the data fusion techniques.
2014 IEEE/ACM 18th International Symposium on Distributed Simulation and Real Time Applications, 2014
In this paper, we design and test a full distributed and scalable resource-management scheduler f... more 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.
The Journal of Supercomputing, 2014
ABSTRACT In this paper, we develop the optimal minimum-energy scheduler for the adaptive joint al... more ABSTRACT 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’s 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 Software-as-a-Service (SaaS) computing model. Our objective is the minimization of the overall computing-plus-communication energy consumption. Main new contribution of the paper the following ones: i) the computing-plus-communication resources 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) in order to deal with the inherently nonconvex nature of the resulting resource optimization problem, a novel resolving approach is developed that leads to the lossless decomposition of the offered problem into the cascade of two simple 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., 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 gaps.
The Journal of Supercomputing
Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks ... more Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks (CycleGANs) are two emerging machine learning models that, up to now, have been used as generative models, i.e., to generate output data sampled from a target probability distribution. However, these models are also equipped with encoding modules, which, after weakly supervised training, could be, in principle, exploited for the extraction of hidden features from the input data. At the present time, how these extracted features could be effectively exploited for classification tasks is still an unexplored field. Hence, motivated by this consideration, in this paper, we develop and numerically test the performance of a novel inference engine that relies on the exploitation of BiGAN and CycleGAN-learned hidden features for the detection of COVID-19 disease from other lung diseases in computer tomography (CT) scans. In this respect, the main contributions of the paper are twofold. First, we...
Applied Sciences, 2021
The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early ... more The recent introduction of the so-called Conditional Neural Networks (CDNNs) with multiple early exits, executed atop virtualized multi-tier Fog platforms, makes feasible the real-time and energy-efficient execution of analytics required by future Internet applications. However, until now, toolkits for the evaluation of energy-vs.-delay performance of the inference phase of CDNNs executed on such platforms, have not been available. Motivated by these considerations, in this contribution, we present DeepFogSim. It is a MATLAB-supported software toolbox aiming at testing the performance of virtualized technological platforms for the real-time distributed execution of the inference phase of CDNNs with early exits under IoT realms. The main peculiar features of the proposed DeepFogSim toolbox are that: (i) it allows the joint dynamic energy-aware optimization of the Fog-hosted computing-networking resources under hard constraints on the tolerated inference delays; (ii) it allows the rep...
Applied Sciences, 2021
The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researc... more The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures ...
Uploads
Papers by Enzo Baccarelli