Sonja Filiposka

Ss. Cyril and Methodius University in Skopje · Faculty of Computer Science and Engineering

STEM (science, technology, engineering and mathematics) education benefits both individuals and society. It supports individuals by increasing their critical-thinking skills, encouraging creativity, as well as providing a basis for new inventions. The underrepresentation of women in STEM is a complex issue with various causes and different approach...

Multi-Access Edge Computing (MEC) based services are becoming very popular in research and innovation areas as there is a high expectation to solve many automation and security problems through wireless connections gathering streaming data that is processed at the edge or cloud layer of the network. Research efforts in this direction normally eithe...

This paper analyses the virtualised entities migration process implementation within the ETSI-compliant edge framework, considering the necessary multi-access edge computing (MEC) modules information interchange required for instantiation, termination and migration of MEC applications. , a communication process that includes network function virtua...

Serverless computing has made a significant impact in the cloud computing landscape, and has even been extended beyond the cloud, up to the edge of the network. Existing serverless platforms which use containers and micro virtual machines as function runtimes incur a significant startup latency, hindering the performance and scalability of the exec...

Edge AI environments are ever increasing as the amount of IoT-connected devices grow, thus rising the level of carbon emissions of such ecosystems. Therefore, sustainable AI cloud/edge systems are a must in order to minimize all those emissions, where AI plays its part in gaining efficiency. In this paper, a scheme to easily organize and optimize t...

Performances analysis of resource management techniques and algorithms for edge computing is a crucial step that reveals the effectiveness of edge service placement and migration strategies in terms of delay and usage. To be able to gauge how different optimisations affect the end user quality of experience a holistic approach is needed, so that th...

Serverless computing, especially when deployed at the edge of the network, is seen as an enabling technology for the future development of more complex Internet of Things systems. However, special care must be taken when deploying new edge infrastructures for serverless workloads in terms of resource usage and network connectivity. Inefficient util...

The quest for knowledge is a defining characteristic of our age. Hybrid learning is an extension of this endeavour, combining in-person and remote training. Due to the COVID-19 outbreak, all classroom activities were moved online. Hybrid learning is here to stay due to its advantages in modern education delivery while satisfying learning objectives...

In order to deal with offloading tasks, fog computing involves a set of distributed hosts, being interconnected according to a certain switching topology, upon which overlay networks may be configured. These type of logical networks will be adapted to fit the needs of different kinds of application flows, resulting in diverse sorts of traffic, each...

Emerging computer paradigms aim to fulfill the ever-present ideal of running as many applications on existing infrastructure, as efficiently as possible. One such novel concept is serverless computing which abstracts away infrastructure management, scaling and deployment from developers, allowing them to host function instances with granular respon...

Serverless computing is a new concept allowing developers to focus on the core functionality of their code, while abstracting away the underlying infrastructure. Even though there are existing commercial serverless cloud providers and open-source solutions, dealing with the explosive growth of new Internet of Things (IoT) devices requires more effi...

Connected health is expected to introduce an improvement in providing healthcare and doctor-patient communication while at the same time reducing cost. Connected health would introduce an even more significant gap between healthcare quality for urban areas with physical proximity and better communication to providers and the portion of rural areas...

Sensor networks deployed for environmental monitoring of ecosystems require battery operation that could last years. Energy conservation is essential to enable a prolonged operation. Inactive states or sleep mode usually consumes orders of magnitude less energy compared to data collection and transmission periods. However, they also last orders of...

This article examines the impact of personality traits, learning styles, gender, and online course factors (course difficulty, group affiliation, provided materials, etc.) in the academic success of students taking online courses and their overall success rate through traditional classes. Students’ performance in the online learning environment is...

Advanced learning algorithms for autonomous driving require lots of processing and storage power, which puts a strain on vehicles’ computing resources. Using a combination of 5G network connectivity with ultra-high bandwidth and low latency together with extra computing power located at the edge of the network can help extend the capabilities of ve...

This paper explores the eParticipation implementation through the usage of web 2.0 tools in the context of local governments in Kosovo, specifically from the perspective of usage practices of such communication platforms, and the potential relationship between the online activity of local governments and the citizen engagement. We have argued that...

Sensitivity of the health-related data and the focus on compliance and security has traditionally emphasized the need for centralized approach while implementing Electronic Health Records (EHR) systems. These one-institutional architectural designs are leading to fragmented and scattered pieces of valuable data across various data warehouses and si...

Fog computing brings distributed computing resources closer to end users, thus allowing for better performance in internet of things applications. In this context, if all necessary resources worked together in an autonomous manner, there might be no need for an orchestrator to manage the whole process, as long as there is no Cloud or Edge infrastru...

Hands-on experience and training related to the latest cyberthreats and best practices, augmented with real-life examples and scenarios is very important for aspiring cybersecurity specialists and IT professionals in general. However, this is not always possible either because of time, financial or technological constraints. For cybersecurity exerc...

Online learning is proving to be a new milestone in education, the advantages that were known from the beginning are now days more appealing and important than ever, the opportunity to learn and teach not depended on location and time and has brought online learning in front of each education institution. We will focus on one dimension of how onlin...

Hands-on experience and training related to the latest cyberthreats and best practices, augmented with real-life examples and scenarios is very important for aspiring cybersecurity specialists and IT professionals in general. However, this is not always possible either because of time, financial or technological constraints. For cybersecurity exerc...

One of the main challenges in edge computing service management is to continuously maintain a high level of quality of service for the end-user mainly in terms of low latency. This can only be achieved with intelligent management of the edge infrastructure virtualised resources making sure that the edge services are always hosted on resources locat...

Edge computing is one of the pillars in the future communication ecosystem that enables enhanced services by offloading the heavy computing to a nearby infrastructure collocated with the access network end points. One of the main challenges in edge computing service management is to continuously maintain a high level of quality of service for the e...

The society is attending to the integration of the IoT technology in many fields related to urban environments, smart homes and industries. The IoT technology is closely related to other emergent technologies such as cloud and fog computing, which provide virtualization services and mobile facilities. For that reason,the development of correct fog/...

Fog computing is an evolution of cloud computing paradigm, whose key point is the location of computing resources at the edge of the network. Data center facilities at the fog level are smaller than those at the cloud level, but nevertheless, they may share similar topologies, such as fat tree or leaf and spine architectures. In this paper, a forma...

One of the main applications of smart cities are parking systems based on IoT/Fog technology. In this paper, we carry out the study of formal algebraic models for such systems. In that context, first of all we undertake the study of a model for a street with a single parking space, extending it with a string of parking spaces. Additionally, we add...

The imminent deployment of 5G and the rapid development of multi-access edge computing standards are demanding advances in terms of vehicular low latency offloading design and modelling proposals. In this paper we describe the functionalities of a high-level multi-access edge computing orchestrator that arranges location based vehicular edge servic...

Online learning is a contemporary concept in which ideas, models, and traditional teachings have changed. We examine how learning style affects the learner's academic achievements in online lessons and gender-specific environments. This research investigates whether VARK styles are associated with course results, regardless of the actual VARK resul...

The Internet of Vehicles requires high bandwidth and low latency services to unleash the potential of fully connected vehicles. Thus, the offloading proposals that successfully manage massive real-time service requests from vehicle nodes are needed. In this paper, we analyse the dynamic resource management for intelligent vehicular networks based o...

Efficient resource management is crucial for balancing performance and energy consumption in large-scale data centres. In the case of additional requirements such as guaranteed resources and low communication latency, it is of great importance to implement not only an efficient initial placement algorithm, but also maximise consolidation by migrati...

Shifting cloud computing capabilities close to the edge enables provisioning of low latency location‐based internet services that are adapted to user behaviour. However, this can be achieved neither with a simple move of the physical hosts closer to edge networks, nor continuing to abide by the same principles as the ones implemented in traditional...

Emerging models such as mobile edge computing provide the necessary characteristics for the deployment of Internet of Things applications by supplying the connected devices with local computing facilities essential for latency sensitive applications. One of the major issues of the underlying edge computing architecture is to cope with the device mo...

Providing realistic production environment for deployment of complex students’ projects can be quite a challenge for the university computing centers. While alternatives such as using public/private clouds exist, enabling the students to focus on core project deployment instead of system administration of a production environment in general require...

Even though there are several different frameworks and standards for proving the digital competencies expected from teachers, there is a need for a Web-based assessment tools that allow real, dependable and valid assessment of these competencies. This paper addresses the design challenges related to a software solution for self-and peer-assessment...

in this paper we seek to understand the outcomes of online education by observing the role of learning styles. Under the assumption that the behaviors that maximize learning are dependent on the delivery method, we compared learning outcomes of students participating in two classes set up on an interactive e-learning platform. Our results show that...

In this paper we seek to better understand the outcomes of online education by observing the role of learner’s personality traits. Under the assumption that the behaviors that maximize learning are dependent on the delivery method, we compared learning outcomes of students participating in two classes set up on an interactive e-learning platform. O...

This demo is envisioned to represent the work done with within JRA2 Service Provider Architecture task in the GEANT project that aims to define and implement an automated OSS/BSS supporting agile service development based on the TMF Frameworx blueprint. The work presented focuses on the challenges of future network operators, where in the OSS/BSS s...

Virtual research environments provide an easy access to e-Infrastructures for researchers by creating an abstracted service-oriented layer on top of the available resources. Using the portal, researchers can focus on the research workflow and data analysis while being provided with a consolidated unified view of all tools necessary for their activi...

Public inclusion is recognized as essential in local government decision-making processes. Popular web based tools not only ensure wide e-participation with increased acceptance among citizens, but can also be used to target long term sustainability by attracting and actively engaging the youth. This paper presents a comprehensive approach aiming t...

The growth of power consumption in Cloud Computing systems is one of the current concerns of systems designers. In previous years, several studies have been carried out in order to find new techniques to decrease the cloud power consumption. These techniques range from decisions on locations for data centres to techniques that enable efficient reso...

The social media have introduced new methods for communication and are providing new opportunities for users to engage in community participation as powerful tools for citizen inclusion in government processes and trust towards eGovernment services. The question raised is to what extent the central government institutions (CGIs) understand the func...

This paper presents results of the ongoing development of the Cloud Services Delivery Infrastructure (CSDI) that provides a basis for infrastructure centric cloud services provisioning, operation and management in multi-cloud multi-provider environment defined as a Zero Touch Provisioning, Operation and Management (ZTP/ZTPOM) model. The presented w...

A number of recent studies use deep belief networks (DBN) with a great success in various applications such as image classification and speech recognition. In this paper, a DBN made up from multiple layers of restricted Boltzmann machines is used for electricity load forecasting. The layer-by-layer unsupervised training procedure is followed by fin...

Accessing ICTs among citizens, especially youth, is gaining momentum as it is assumed to contribute to increased participation and general improvement in citizens’ present and future welfare. The move to create opportunities for engagement of youth in processes of urban planning represents one common vision for empowering local communities with ICT...

We show that three basic actor characteristics, namely normalized reciprocity, three cycles, and triplets, can be expressed using an unified framework that is based on computing the similarity index between two sets associated with the actor: the set of her/his friends and the set of those considering her/him as a friend. These metrics are extended...

p>This paper presents results of the ongoing development of the Cloud Services Delivery Infrastructure (CSDI) that provides a basis for infrastructure centric cloud services provisioning, operation and management in multicloud multi-provider environment defined as a Zero Touch Provisioning, Operation and Management (ZTP/ZTPOM) model. The presented...

In order to obtain an efficient wireless sensor network localization, several enhancements based on the decentralized approach are proposed. These features can be used in the cases when multiple distance measurements are used as input, where each node iteratively updates its estimated position using a maximum likelihood estimation method based on t...

Optimal usage of data center resources has become one of the most important topics in the cloud computing research community. Increased efficiency alongside decreased power consumption becomes a desired goal. Crucial point in achieving this goal is the process of virtual machine placement. In this paper, we analyze and compare several heuristics ai...

The ongoing trends in cloud computing demonstrate increasing need for efficient, yet economical data centers. Thus, recently the research community has focused its efforts on frameworks for optimised usage of the available resources that will result with energy-efficient and highly effective data centers. Toward this goal, in this paper we present...

Modern research and education networks need to solve two major tasks: (1) providing seamless access to their users, and (2) support new scientific and collaborative applications that are becoming increasingly complex and dynamic in their scale, use of distributed resources, and required advanced networking services. Rapid deployment and automation...

With the emergence of web 2.0 the web has evolved from informational posting board to rich application platform. Web applications have replaced desktop applications from office productivity to 3d rendering. In this paper we'll present issues that degrade user web experience and increase demand for resource as well as techniques for mitigating those...

For over a decade, the data requirements of e-Science applications increase drastically with the emergence of data-intensive applications. The efficient usage of these complex applications that involve the composition of services horizontally, but also vertically across multiple networks, demand a guaranteed level of quality of service to be provid...

In this paper we present a parallel implementation of the Durkins radio propagation algorithm on Nvidia GPU devices. We have modified the extension of the NS-2 network simulator, by developing a transparent module which uses the Durkins parallel algorithm for simulation of wireless mobile networks over 3D terrains. When evaluating the performance o...

Nowadays, companies collect data at an increasingly high rate to the extent that traditional implementation of algorithms cannot cope with it in reasonable time. On the other hand, analysis of the available data is a key to the business success. In a Big Data setting tasks like feature selection, finding discretization thresholds of continuous data...

A method for sampling rare events throughout hybrid statistical physics quantum mechanical studies of hydrophobic interactions in liquid phases was analyzed and implemented on GPU architecture. The rare events considered in the present case are related to formation of the so-called dangling X-H bonds of small polar solvent molecules around notably...

In this paper we propose a parallel implementation of the algorithm for computation of information gain with the services of the Hadoop ecosystem: MapReduce, HDFS, HBase and Yarn (MapReduce). The proposed implementation can be used for ranking features of large datasets and furthermore for feature selection. We use the Cloudera distribution of Hado...

Analysing and understanding people’s communication patterns and behavior provide insight into human habits and their typical actions on different timescales. Combining these results with data available from other important sectors enables the study of the interrelationship and influence of major external events on the changes in the “normal” commun...

GEANT4 OCX Research and Development Focus Areas

In this paper we present a general technique for parallelizing regular algorithms with the tools the Hadoop ecosystem offers: MapReduce, HDFS, HBase and Pig. This framework can be applied for parallelizing algorithms for feature selection, clustering, machine learning etc. It consists of several steps: load the datasets in HDFS, apply some transfor...

This paper presents results of the ongoing development of the Open Cloud eXchange (OCX) that has been proposed in the framework of the GN3plus project. Its aim is to provide cloud aware network infrastructure to power and support modern data intensive research at European universities and research organisations. The paper describes the OCX concept,...

The communication infrastructure is a critical component of a large-scale cloud data center. It needs to provide the best performance available while keeping overprovisioning and, lately even more important, power consumption, to the minimum. Aiming to provide a unified solution that will have high performance together with economical benefits and...

Recognizing the unsustainability in designing power hungry HPC systems, in the recent years an effort towards an energy and performance efficient HPC design is on the rise. Based on the available data on top green HPC systems, in this paper we analyze the main components of the HPC system with the attempt to provide an insight into the green effici...

Ever since the start of the green HPC initiative, a new design constriction has appeared on the horizon for the top supercomputer designers. Today's top HPCs must not only boast with their exascale performances, but must take into account reaching the new exaflops frontiers with as minimum power consumption as possible. The goals of this paper are...

The network architecture deployed in a data center is of extreme importance and should provide the data center with the high throughput while keeping overprovisioning at the minimum costs. In order to provide these features new complex network based models have been proposed recently. In this paper we give an overview of the proposed models and the...

In the recent years, computing is shifting from “central processing” on the CPU to “co-processing” on the CPU and GPU. This computing paradigm shift is due to the development of CUDA (Compute Unified Device Architecture) parallel computing architecture. CUDA is a programming model for parallel computing in Graphics Processing Units (GPUs). In this...

Because of rapidly growing subscriber populations, advances in cellular communication technology, increasingly capable user terminals, and the expanding range of mobile applications, cellular networks have experienced a significant increase in data traffic. Smartphone traffic contributes a considerable amount to Internet traffic. The increasing pop...

This paper presents the concept of Open Cloud eXchange (OCX) that has been proposed by the GN3plus JRA1 activity to bridge the gap between two major components of the cloud services provisioning infrastructure: Cloud Service Provider (CSP) infrastructure; and cloud services delivery infrastructure which in many cases requires dedicated local infras...

In this paper we give an overview of the cloud computing benefits for the educational institutions as well as risks that must not be overlooked when embarking on this type of venture. We review a number of success stories from all over the world about implementing cloud computing into the educational process on small and big scales. We also discuss...

Achieving seamless handover between different wireless technologies, known as vertical handover, is a major challenge for the next generation wireless networks. In order to achieve seamless continuous connection and select the best network, it is vital to have a good decision making algorithm. In this paper an extensive review and cross comparison...

This document proposes an initial GÉANT Open Cloud eXchange (gOCX) architecture, taking into account the background environment in which it will operate. It presents a brief overview of related projects, as well as possible extensions.