Article
Computer Science, Information Systems
Anatoliy Zabrovskiy, Prateek Agrawal, Vladislav Kashansky, Roland Kersche, Christian Timmerer, Radu Prodan
Summary: This study examines the performance and optimized selection of Amazon EC2 spot instances for video encoding. The results demonstrate that by optimizing the selection of EC2 spot instances, video encoding costs can be significantly reduced.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Automation & Control Systems
Boyi Liu, Lujia Wang, Ming Liu
Summary: This article presents RoboEC2, a novel cloud robotic system that utilizes Amazon EC2 for dynamic network offloading. It introduces a cloud-edge cooperation framework based on ROS and AWS and a network offloading approach with dynamic splitting. RoboEC2 is flexible, convenient, and robust, and it is the first cloud robotic system with no constraints on time, location, or computing power.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Sharmistha Mandal, Giridhar Maji, Sunirmal Khatua, Rajib K. Das
Summary: Cloud Service Providers offer different pricing schemes and Cloud Service Users can choose on-demand, reserved, or spot instances. The optimal reservation amount is a significant research problem, especially when using spot instances with unpredictable prices. We proposed two algorithms to determine the reservation amount without knowing the future spot prices. Our algorithm ensures a cost within a factor 2 - u(h)/e(c) of the optimal cost, where u(h) is the usage cost per hour of the reserved instance and e(c) is the average cost per hour for unreserved instances. Experimental results show that our algorithm differs from ILP by less than 21% in cost.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Rania Ben Halima, Slim Kallel, Mehdi Ahmed Nacer, Walid Gaaloul
Summary: Cloud computing is a rapidly growing technology that aims to improve performance levels and reduce operational costs. This paper presents an approach to assist business process designers in finding optimal assignment or scheduling based on various pricing strategies. Experimental results demonstrate the feasibility, effectiveness, and performance of the approach.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Management
Ludwig Dierks, Sven Seuken
Summary: This study analyzes the viability of offering a spot market in cloud computing by combining queueing theory and game theory. The findings show that a provider can achieve a profit increase and create a Pareto improvement for users by offering a spot market alongside a fixed-price market.
MANAGEMENT SCIENCE
(2022)
Article
Computer Science, Theory & Methods
Amelie Chi Zhou, Jianming Lao, Zhoubin Ke, Yi Wang, Rui Mao
Summary: This article presents FarSpot, an optimization framework for HPC applications in the latest cloud spot market that aims to minimize application cost while ensuring performance constraints. FarSpot utilizes accurate long-term price prediction and a cost-aware deadline assignment algorithm to reduce the monetary cost of HPC applications.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Mathematics
Lining Xing, Rui Wu, Jiaxing Chen, Jun Li
Summary: This study explores the characteristics of cloud resources and workflow structures to design a knowledge-based evolutionary optimization operator, named KEOO, with two novel features. The KEOO algorithm includes a task consolidation mechanism to reduce the number of cloud resources used and a critical task adjustment mechanism to eliminate data transmission overhead. Experimental results demonstrate the effectiveness of KEOO in improving existing multi-objective algorithms for solving cloud workflow scheduling problems.
Article
Computer Science, Information Systems
George Fragiadakis, Evangelia Filiopoulou, Christos Michalakelis, Thomas Kamalakis, Mara Nikolaidou
Summary: This study uses machine learning to predict the price model of reserved instances in the cloud service market based on historical data. Preliminary results show that the machine learning model accurately captures the evolution patterns and predicts trends.
Article
Computer Science, Information Systems
Mohan Baruwal Chhetri, Abdur Rahim Mohammad Forkan, Quoc Bao Vo, Surya Nepal, Ryszard Kowalczyk
Summary: Consumers can reduce the ongoing costs and the risk of resource revocation for cloud applications by diversifying their resource contracts and types.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Mohan Baruwal Chhetri, Abdur Rahim Mohammad Forkan, Quoc Bao Vo, Surya Nepal, Ryszard Kowalczyk
Summary: This paper introduces a novel opportunistic resource scaling approach that leverages resource and contract heterogeneity for cost-effective resource allocations. The results show that this approach, especially full capacity optimization, outperforms traditional scaling methods and offers significant cost savings.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Bianca G. Magalhaes, Pedro M. R. Bento, Jose A. N. Pombo, Maria R. A. Calado, Silvio J. P. S. Mariano
Summary: The paper proposes an electricity trading strategy based on a mid-term forecast of the average spot price and a risk premium analysis. The forecast model uses an Artificial Neural Network trained with the Long Short Term Memory architecture. Statistical analysis verifies the correlation and dependency between variables and the results indicate benefits for traders adopting the proposed trading strategy.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Changyuan Lin, Hamzeh Khazaei
Summary: The study addresses two issues related to the performance and cost prediction and optimization of serverless applications, proposing a new framework and algorithm to achieve accurate configurations. The analytical models show over 98% accuracy in predicting performance and cost, while the PRCP algorithm can optimize serverless applications with 97% accuracy on average.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2021)
Article
Economics
Paulina A. Rowinska, Almut E. D. Veraart, Pierre Gruet
Summary: The study introduces a four-factor arithmetic model for electricity baseload spot prices in Germany and Austria, incorporating deterministic and stochastic components as well as exogenous factors. It was found that considering the impact of wind energy generation on prices improves model fit.
Article
Computer Science, Information Systems
Guangba Yu, Pengfei Chen, Zibin Zheng
Summary: Microservices have gained popularity in constructing cloud native systems due to their agility. However, determining and evaluating resource requirements for scaling is a challenging task in microservice applications due to their complexity. In this article, the authors present a novel system called Microscaler that automatically identifies scaling-needed services in microservice applications and scales them to meet SLA requirements with optimal cost. Microscaler collects QoS metrics and uses a service dependency graph to determine under- or over-provisioned service instances. By combining online learning and a heuristic approach, Microscaler achieves precise scaling meeting SLA requirements faster than other methods.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Computer Science, Theory & Methods
Changyuan Lin, Nima Mahmoudi, Caixiang Fan, Hamzeh Khazaei
Summary: This study fills the gap in predictability and performance-cost trade-off of Function-as-a-Service (FaaS) applications by proposing formal performance and cost modeling and optimization algorithms. The proposed model and algorithms enable accurate prediction and fine-grained control over the performance and cost of FaaS applications, helping developers make informed decisions.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2023)
Article
Engineering, Civil
Bogumil Kaminsk, Lukasz Krainski, Atefeh Mashatan, Pawel Pralat, Przemyslaw Szufel
JOURNAL OF ADVANCED TRANSPORTATION
(2020)
Article
Management
Marlin Ulmer, Maciek Nowak, Dirk Mattfeld, Bogumil Kaminski
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2020)
Article
Mathematics, Applied
Reaz Huq, Bogumil Kaminski, Atefeh Mashatan, Pawel Pralat, Przemyslaw Szufel
Summary: The paper investigates the broadcasting process on road networks, and provides tight bounds for broadcasting time that hold asymptotically almost surely for the whole range of the parameter k by analyzing the family of complete graphs. These theoretical results reveal interesting relationships and help understand and explain the behavior observed in more realistic networks.
DISCRETE APPLIED MATHEMATICS
(2021)
Article
Engineering, Civil
Przemyslaw Szufel, Bartosz Pankratz, Anna Szczurek, Bogumil Kaminski, Pawel Pralat
Summary: This paper proposes a multiagent, large-scale vehicle routing modeling framework to simulate transportation systems. The goals are to investigate the interaction between individual and social knowledge and their impact on traffic flow, and to evaluate the effects of different discrete-event simulation designs. The approach combines efficient discrete-event modeling with intelligent drivers who can learn from individual experience and widely available social knowledge. It is applied to modeling commuter behavior in Winnipeg, Manitoba, Canada.
JOURNAL OF ADVANCED TRANSPORTATION
(2022)
Article
Computer Science, Artificial Intelligence
Bogumil Kaminski, Tomasz Olczak, Bartosz Pankratz, Pawel Pralat, Francois Theberge
Summary: This paper investigates the properties and performance of synthetic random graph models with a built-in community structure, and proposes a multi-threaded graph generator ABCDe. The ABCDe generator is more efficient and scalable than the previously available sequential version and the parallel implementation of LFR. The generated random graphs by ABCD have similar properties to the ones generated by the original LFR algorithm.
Article
Economics
Maria Aluchna, Benson Honig, Bogumil Kaminski
Summary: This study examines the gender bias related to the impact of women in executive management leadership. It finds that men are more likely to be hired in executive roles, while women are more likely to be appointed to executive boards in underperforming companies. Additionally, higher participation of women in executive positions is associated with lower long-term value.
POST-COMMUNIST ECONOMIES
(2023)
Article
Medicine, General & Internal
Jakub Perwieniec, Krzysztof Podwojcic, Michal Maluchnik, Mateusz Szelag, Dorota Walkiewicz, Michal Zakrzewski, Amelia Drozdzikowska, Bogumil Kaminski, Adriana Zasybska, Marcin Wnuk, Agnieszka Slowik, Konrad Rejdak
Summary: The study compared a wide spectrum of prodromal signs and symptoms between males and females in the 7-year period before the definite diagnosis of MS. Significant differences were found in symptom groups between genders, with women showing more musculoskeletal, ophthalmic, laryngological, digestive, urinary, mental, cardiovascular, complaints and headaches symptoms, while men showing more musculoskeletal, ophthalmic, laryngological, cardiovascular symptoms, headaches symptoms, and an overrepresentation of reproductive system problems. Peptides with woman (p < 0.001 ) Carlton peptide was set skin and ..
. Reproductive system problems in men..
In the case of urinary problems... and collagen in ( p < 0.05 ) Information rich... Data on race from the.. a fact now... In man's water... Data ketamine.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Social Sciences, Mathematical Methods
Bogumil Kaminski, Pawel Pralat, Francois Theberge
Summary: Most current complex networks have community structure, algorithms aim to take advantage of communities but are often sensitive and cannot be fine-tuned for real networks. Testing algorithms on synthetic graphs with built-in community structure is crucial.
Article
Economics
Jacek Filipowski, Bogumil Kaminski, Atefeh Mashatan, Pawel Pralat, Przemyslaw Szufel
Summary: In this paper, the problem of increasing transportation system efficiency through optimizing commuters' behavior is considered. A bidding mechanism is introduced to reduce traffic in congested streets, leading to a more efficient allocation of routes or means of transportation chosen by commuters. The proposed method is verified through an agent-based simulation model in a real city setting, confirming its effectiveness in improving traffic efficiency.
ECONOMICS OF TRANSPORTATION
(2021)
Article
Mathematics, Interdisciplinary Applications
Bogumil Kaminski, Pawel Pralat, Francois Theberge
JOURNAL OF COMPLEX NETWORKS
(2020)
Article
Business
Maria Aluchna, Bogumil Kaminski, Brinda Mahadeo
CORPORATE GOVERNANCE-THE INTERNATIONAL JOURNAL OF BUSINESS IN SOCIETY
(2020)
Article
Computer Science, Interdisciplinary Applications
Shivani Sharma, Sateesh Kumar Awasthi
Summary: Vehicular Ad-hoc Network (VANET) is crucial in Intelligent Transportation Systems, and this study proposes a hybrid system utilizing V2V and V2I communications for secure data dissemination in urban scenarios.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Hind Mikram, Said El Kafhali, Youssef Saadi
Summary: Efficient task scheduling in cloud data centers is crucial for optimizing resource utilization and load balance. This paper introduces a hybrid algorithm, HEPGA, that combines particle swarm optimization (PSO) and genetic algorithm (GA) to allocate tasks efficiently and minimize makespan in cloud computing environments. By integrating PSO, GA, and HEFT-based initialization, the algorithm capitalizes on parallel processing capabilities and adapts to varying priorities to enhance resource utilization. Meticulous analysis of the algorithm's performance, considering both makespan and resource utilization, demonstrates its ability to consistently allocate resources and adapt to different optimization goals.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Ping-Chen Chang, Cheng-Fu Huang, Ding-Hsiang Huang
Summary: This paper introduces a novel simulation approach based on minimal cuts to estimate the system reliability of a multistate flow network (MSFN). The approach improves computational efficiency by reducing the number of minimal cuts and preserving saturated minimal cuts. It effectively deals with non-integer demands and demonstrates effectiveness and efficiency in illustrative examples.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Jang Won Bae, Chun-Hee Lee, Jeong-Woo Lee, Seon Han Choi
Summary: In this study, a data-driven agent-based model is proposed for simulating the public bicycle-sharing systems (PBSSs) in Sejong City, South Korea. The model captures users' behavioral characteristics and analyzes their convenience through a bottom-up approach. By extracting parameters from actual operational data and demographic information, the model's accuracy is improved. Model simulations evaluate the utilization and user convenience of Eoulling, providing a viable solution for addressing multiple concerns.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Chong Shi, Junbao Pian, Cong Zhang, Xiao Chen, Yonggang Zhang
Summary: This study presents a novel numerical simulation method for analyzing the mechanisms of pulsed pressure-induced rock fractures. The results show that rock fracturing under impulsive loading is a combined effect of stress waves and high-pressure fluids, with the fluid penetration and splitting action playing important roles in the process.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Junwei Zhang, Zhongwei Chen, Kang Shao
Summary: This study investigated the performance of three constitutive models for rock material in simulation of blast-induced rock cracks, and proposed an optimal blasting parameters design.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Joshua Shakya, Chaima Ghribi, Leila Merghem-Boulahia
Summary: Modeling and simulation of telecommunication networks, especially 5G+ networks, have become increasingly important and challenging. Traditional simulation techniques may not be sufficient to capture the dynamic changes in 5G+ networks, leading researchers to adopt an Agent-based modeling and simulation approach from the perspective of Complex System Science. This study provides insights into the advantages, potential, and challenges of Agent-based simulation in the context of 5G+ networks, and proposes a prospective architecture for a simulator and its evolution into a Digital Twin.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)
Article
Computer Science, Interdisciplinary Applications
Sensen Xing, Cheng Wang, Wei Wang, Rui Feng Cao, Anthony Chun Yin Yuen, Eric Wai Ming Lee, Guan Heng Yeoh, Qing Nian Chan
Summary: This paper proposes an extended FFCA model that integrates the natural step length into pedestrian movement, allowing pedestrians to occupy multiple grids and expanding the interaction area. Through simulation of evacuation scenarios, the model accurately reproduces density-velocity relations and matches experimental results. Compared to traditional models, this model generates more reasonable velocity variations and evacuation paths.
SIMULATION MODELLING PRACTICE AND THEORY
(2024)