Klodiana Goga

Simulation, Modeling, and Performance Evaluation Tools for Cloud Applications

As cloud computing adoption and deployment increase, the performance evaluation of the cloud environments is becoming very important. Cloud applications have different composition, configuration, and deployment requirements. Simulation and modeling techniques are suitable to quantify the performance of resource allocation policies and application scheduling algorithms in Cloud computing environments for different application and service models according to different work loads, energy performance and system size. In this paper, we give an overview of the existing distributed systems simulation and modeling tools in order to outline the main characteristics and peculiarities. We then present an outlook on new requirements to be addressed for performance evaluation of cloud applications through simulation and modeling.

A Hybrid Cloud Infrastructure for the Optimization of VANET Simulations

Cloud computing is becoming increasingly popular for the provisioning of computing resources, in particular, through scientific tools that perform modeling or simulations. Vehicular Ad-Hoc Networks (VANETs) are mobile ad hoc networks which are meant to support primarily safety warnings and to manage challenging conditions to improve our transportation experience. This is a challenging context where large amounts of data need to be elaborated and analyzed in order to fully understand protocol and phenomena behaviors. In fact, VANET simulations are typically computationally intensive problems, and lend themselves for execution on distributed systems. A new hybrid cloud infrastructure is here presented to help and support the simulation science. This architecture optimizes the scheduling and execution of a batch of simulations, increasing the overall performance, in terms of simulation time and costs. Results clearly highlight the potentiality of this technology, proving as a valuable tool for network simulations.

Performance Analysis of the DInSAR P-SBAS Algorithm within AWS Cloud

Often scientific applications are characterized by complex workflows and large datasets to manage. Usually, these applications run in dedicated high performance computing centers with low-latency interconnections which require a consistent initial cost. Public and private cloud computing environments, thanks to their features such as customized computing environments, flexibility, and elasticity represent a valid alternative with respect to HPC clusters in order to minimize costs and optimize processing. In this paper the migration of an advanced Differential Synthetic Aperture Radar Interferometry (DInSAR) methodology for the investigation of Earth surface deformation phenomena to the Amazon Web Services (AWS) cloud computing environment is presented. Such a technique which is referred to as Parallel Small Baseline Subset (P-SBAS) algorithm allows producing mean deformation velocity maps and the corresponding displacement time-series from a temporal sequence of radar images. Moreover, an experimental analysis aimed at evaluating the P-SBAS algorithm parallel performances which are achieved within the AWS cloud by exploiting two different families of instances and by taking into account different I/O and network bandwidth configurations is presented.

Design and Quantitative Assessment of a Novel Hybrid Cloud Architecture for VANET Simulations

Vehicular Ad-hoc NETworks (VANETs) are ad hoc networks aimed at improving the safety and efficiency of transportation in the near future. Despite the availability of results from field trials, simulations still play an unequalled role in the comprehensive understanding of complex and crowded VANET scenarios. Even more, VANET simulations are typically computationally intensive problems and lend themselves for execution on distributed systems. This paper presents a new architecture optimizing the scheduling and execution of a batch of simulations over a hybrid cloud. Results reveal that, in case of multiple simulations to be executed, the overall performance can deeply benefit from a distributed approach, reducing time and costs.

Performance Analysis of WRF Simulations in a Public Cloud and HPC Environment

The Weather Research and Forecasting (WRF) Model is a numerical weather prediction system designed for both atmospheric research and operational forecasting needs. WRF requires a large amount of CPU power which increases drastically if WRF is used to model a big geographical area with a high resolution. To satisfy the computational demand WRF requires large number of computing resources through infrastructures such as clusters in grid or cloud. In this paper the performance analysis of different WRF simulations to the Amazon Web Services (AWS) cloud computing environment (single node and cluster) compared to that of a HCP cluster is presented.

Automated Cloud Computing Approach for the Simulation of Chemo-Hydrodynamic Problems

Studying the interplay between hydrodynamic instabilities and chemical reactions is attracting increasing interest because of its transversal impact ranging from fundamental to applied science. Depending on the case of study, the exploration of Reaction-Diffusion-Convection (RDC) dynamics over a significant spatio-temporal domain can be computationally expensive and convergence issues may arise in the presence of steep gradients of the chemical or the hydrodynamic fields. Cloud automation techniques allow to create in an easy and dynamical way an arbitrarily large number of virtual nodes, tailored on the specific problem at hands. In this work we show the first steps towards a fully automated and flexible platform for the simulation of chemo-hydrodynamic problems in a cloud environment.

Cyber Kill Chain Defender for Smart Meters

The transition to generation-led approach in Smart Grids assigns new roles to networked Demand-oriented Real-time Smart Meters that operate in decentralized system. In new operational scenario, to achieve network-wide interoperability, smart meters are exposed to cyber threats. One of the mostly known risks is so-called Cyber Kill Chain. This research article discusses about a work performed in the context of SUCCESS (Energy) Horizon-2020 project on early detection of stages of the Cyber Kill Chain in Advanced Metering Infrastructures of modern Smart Grids. The authors discuss about patterns allowing early detection of Reconnaissance activities and the use of Artificial Intelligence pattern matching methods.

Towards Energy Efficient Orchestration of Cloud Computing Infrastructure

The emerging of new Cloud services and applications demanding for ever more performance (i.e., on one hand, the rapid growth of applications using deep learning –DL, on the other hand, HPC-oriented work-flows executed in Cloud) is continuously putting pressure on Cloud providers to increase capabilities of their large data centers, by embracing more advanced and heterogeneous devices [2, 3, 11]. Hardware heterogeneity also helps Cloud providers to improve energy efficiency of their infrastructures by using architectures dedicated to specific workloads. However, heterogeneity represents a challenge from the infrastructure management perspective. In this highly dynamic context, workload orchestration requires advanced algorithms to not defeat the efficiency provided by the hardware layer. Despite past works partially addressed the problem, a comprehensive solution is still missing.

Performance of WRF Cloud Resolving Simulations with Data Assimilation on Public Cloud and HPC Environments

The Weather Research and Forecasting (WRF) model is a numerical weather prediction system commonly used for atmospheric research and operational forecasting. Given the great amount of computing resources needed by this model, a HPC or cloud computing infrastructure is needed. In this paper, high resolution simulations (1 km) with data assimilation have been ran on different configurations in Amazon Web Services Cloud computing environment, comparing the performance obtained with different computing sizes and storage technologies. A comparison between performance obtained with a Cloud computing setup and a HPC cluster has also been made.

An Evaluation of Neural Networks Performance for Job Scheduling in a Public Cloud Environment

Artificial Neural Networks (ANNs) represent a family of powerful machine learning-based techniques used to solve many real-world problems. The various applications of ANNs can be summarized into classification or pattern recognition, prediction and modeling. As with other machine learning techniques, ANNs are getting momentum in the Big Data era for analysing, predicting and Big Data analytics from large data sets. ANNs bring new opportunities for Big Data analysis for extracting accurate information from the data, yet there are also several challenges to be faced not known before with traditional data sets. Indeed, the success of learning and modeling Big Data by ANNs varies with training sample size, depends on data dimensionality, complex data formats, data variety, etc. In particular, ANNs performance is directly influenced by data size, requiring more memory resources. In this context, and due to the assumption that data set may no longer fit into main memory, it is interesting to investigate the performance of ANNs when data is read from main memory or from the disk. This study represents a performance evaluation of Artificial Neural Network (ANN) with multiple hidden layers, when training data is read from memory or from disk. The study shows also the trade-offs between processing time and data size when using ANNs.