Marios Perlitis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marios Perlitis has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Basilis Mamalis
University of West Attica, Athens, Greece
3 shared publications
Latest Publications
- Open Access
Steady and Energy-Efficient Multi-Hop Clustering for Flying Ad-Hoc Networks (FANETs)
Flying Ad-hoc Networks (FANETs), formed by Unmanned Aerial Vehicles (UAVs), represent an emerging and promising communication paradigm. These networks face unique challenges due to UAVs high mobility, limited energy resources, and dynamic topology. In this work, we propose a novel multi-hop clustering algorithm aimed at creating stable, energy-efficient clusters in FANET environments. The proposed solution enhances cluster longevity and communication efficiency through mobility-aware clustering, energy-centric cluster head (CH) selection, and a ground station(GS)-assisted cluster maintenance management mechanism. First, steady multi-hop clusters are constructed, having CHs with not only high stability and high energy but also with steady and high-energy neighboring areas, and then a proper GS-assisted cluster maintenance mechanism is applied. Experimental results, based on extended simulations, demonstrate that our approach outperforms existing schemes significantly, in terms of cluster stability, communication overhead, and security resilience.
Open AccessSteady and Energy-Efficient Multi-Hop Clustering for Flying Ad-Hoc Networks (FANETs)
Flying Ad-hoc Networks (FANETs), formed by Unmanned Aerial Vehicles (UAVs), represent an emerging and promising communication paradigm. These networks face unique challenges due to UAVs high mobility, limited energy resources, and dynamic topology. In this work, we propose a novel multi-hop clustering algorithm aimed at creating stable, energy-efficient clusters in FANET environments. The proposed solution enhances cluster longevity and communication efficiency through mobility-aware clustering, energy-centric cluster head (CH) selection, and a ground station(GS)-assisted cluster maintenance management mechanism. First, steady multi-hop clusters are constructed, having CHs with not only high stability and high energy but also with steady and high-energy neighboring areas, and then a proper GS-assisted cluster maintenance mechanism is applied. Experimental results, based on extended simulations, demonstrate that our approach outperforms existing schemes significantly, in terms of cluster stability, communication overhead, and security resilience.
- Open Access
Improved Task Scheduling for Virtual Machines in the Cloud based on the Gravitational Search Algorithm
The rapid and convenient provision of the available computing resources is a crucial requirement in modern cloud computing environments. However, if only the execution time is taken into account when the resources are scheduled, it could lead to imbalanced workloads as well as to significant under-utilisation of the involved Virtual Machines (VMs). In the present work a novel task scheduling scheme is introduced, which is based on the proper adaptation of a modern and quite effective evolutionary optimization method, the Gravitational Search Algorithm (GSA). The proposed scheme aims at optimizing the entire scheduling procedure, in terms of both the tasks execution time and the system (VMs) resource utilisation. Moreover, the fitness function was properly selected considering both the above factors in an appropriately weighted function in order to obtain better results for large inputs. Sufficient simulation experiments show the efficiency of the proposed scheme, as well as its excellence over related approaches of the bibliography, with similar objectives.
Open AccessImproved Task Scheduling for Virtual Machines in the Cloud based on the Gravitational Search Algorithm
The rapid and convenient provision of the available computing resources is a crucial requirement in modern cloud computing environments. However, if only the execution time is taken into account when the resources are scheduled, it could lead to imbalanced workloads as well as to significant under-utilisation of the involved Virtual Machines (VMs). In the present work a novel task scheduling scheme is introduced, which is based on the proper adaptation of a modern and quite effective evolutionary optimization method, the Gravitational Search Algorithm (GSA). The proposed scheme aims at optimizing the entire scheduling procedure, in terms of both the tasks execution time and the system (VMs) resource utilisation. Moreover, the fitness function was properly selected considering both the above factors in an appropriately weighted function in order to obtain better results for large inputs. Sufficient simulation experiments show the efficiency of the proposed scheme, as well as its excellence over related approaches of the bibliography, with similar objectives.
- Open Access
A Hybrid Multi-GPU Implementation of Simplex Algorithm with CPU Collaboration
The simplex algorithm has been successfully used for many years in solving linear programming (LP) problems. Due to the intensive computations required (especially for the solution of large LP problems), parallel approaches have also extensively been studied. The computational power provided by the modern GPUs as well as the rapid development of multicore CPU systems have led OpenMP and CUDA programming models to the top preferences during the last years. However, the desired efficient collaboration between CPU and GPU through the combined use of the above programming models is still considered a hard research problem. In the above context, we demonstrate here an excessively efficient implementation of standard simplex, targeting to the best possible exploitation of the concurrent use of all the computing resources, on a multicore platform with multiple CUDA-enabled GPUs. More concretely, we present a novel hybrid collaboration scheme which is based on the concurrent execution of suitably spread CPU-assigned (via multithreading) and GPU-offloaded computations. The experimental results extracted through the cooperative use of OpenMP and CUDA over a notably powerful modern hybrid platform (consisting of 32 cores and two high-spec GPUs, Titan Rtx and Rtx 2080Ti) highlight that the performance of the presented here hybrid GPU/CPU collaboration scheme is clearly superior to the GPU-only implementation under almost all conditions. The corresponding measurements validate the value of using all resources concurrently, even in the case of a multi-GPU configuration platform. Furthermore, the given implementations are completely comparable (and slightly superior in most cases) to other related attempts in the bibliography, and clearly superior to the native CPU-implementation with 32 cores.
Open AccessA Hybrid Multi-GPU Implementation of Simplex Algorithm with CPU Collaboration
The simplex algorithm has been successfully used for many years in solving linear programming (LP) problems. Due to the intensive computations required (especially for the solution of large LP problems), parallel approaches have also extensively been studied. The computational power provided by the modern GPUs as well as the rapid development of multicore CPU systems have led OpenMP and CUDA programming models to the top preferences during the last years. However, the desired efficient collaboration between CPU and GPU through the combined use of the above programming models is still considered a hard research problem. In the above context, we demonstrate here an excessively efficient implementation of standard simplex, targeting to the best possible exploitation of the concurrent use of all the computing resources, on a multicore platform with multiple CUDA-enabled GPUs. More concretely, we present a novel hybrid collaboration scheme which is based on the concurrent execution of suitably spread CPU-assigned (via multithreading) and GPU-offloaded computations. The experimental results extracted through the cooperative use of OpenMP and CUDA over a notably powerful modern hybrid platform (consisting of 32 cores and two high-spec GPUs, Titan Rtx and Rtx 2080Ti) highlight that the performance of the presented here hybrid GPU/CPU collaboration scheme is clearly superior to the GPU-only implementation under almost all conditions. The corresponding measurements validate the value of using all resources concurrently, even in the case of a multi-GPU configuration platform. Furthermore, the given implementations are completely comparable (and slightly superior in most cases) to other related attempts in the bibliography, and clearly superior to the native CPU-implementation with 32 cores.