Article
Computer Science, Hardware & Architecture
Jakub Beranek, Stanislav Bohm, Vojtech Cima
Summary: Task graphs provide a simple way to describe scientific workflows that can be executed on HPC clusters and in the cloud, with scheduling algorithms being an important aspect. However, previous works have often overlooked the quantification of the impact of scheduling challenges, leading to potentially significant discrepancies in results when compared to more realistic models. Properly describing implementation details of scheduling algorithms is crucial for enabling accurate evaluation and maximizing scheduler performance.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Information Systems
Qin-zhe Xiao, Jinghui Zhong, Liang Feng, Linbo Luo, Jianming Lv
Summary: This paper proposes a cooperative coevolution hyper-heuristic framework to solve the workflow scheduling problem, aiming to minimize the completion time of the workflow. The framework automatically learns the task selection rule and resource selection rule using a cooperative coevolution genetic programming algorithm. A set of low-level heuristics is defined to improve the search efficiency. Experimental results demonstrate the superior performance of the proposed framework on multiple metrics.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Mehboob Hussain, Ming-Xing Luo, Abid Hussain, Muhammad Hafeez Javed, Zeeshan Abbas, Lian-Fu Wei
Summary: Cloud computing provides resources to users on a pay-as-you-go model, meeting their computing and storage needs. A private cloud is a cost-saving option with user-owned resources, while the public cloud is the only choice when private cloud resources are insufficient. In this study, a proposed algorithm called Deadline-constrained Cost-aware Workflow Scheduling (DCWS) addresses task scheduling problems in hybrid cloud environments. The algorithm optimizes task execution on the private cloud and utilizes the public cloud for unscheduled tasks, considering task precedence and deadline constraints.
SIMULATION MODELLING PRACTICE AND THEORY
(2023)
Article
Engineering, Manufacturing
Minglong Zhou, Melvyn Sim, Shao-Wei Lam
Summary: The study addresses the issue of advance scheduling of ward admission requests in a public hospital and proposes a resource satisficing framework to reduce the risks of resource overutilization.
PRODUCTION AND OPERATIONS MANAGEMENT
(2022)
Article
Computer Science, Information Systems
K. Kalyana Chakravarthi, P. Neelakantan, L. Shyamala, V. Vaidehi
Summary: This paper discusses the importance of resource provisioning and workflow execution in a multi-cloud environment using a pay-as-you-use framework. It proposes a Normalization based Reliable Budget constraint Workflow Scheduling (NRBWS) algorithm to improve the reliability of workflow execution and reduce the makespan under the budget constraint. Simulation results demonstrate that the proposed algorithm outperforms existing heuristics.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Hao Wu, Xin Chen, Xiaoyu Song, Chi Zhang, He Guo
Summary: This paper presents a novel task scheduling framework named COMSE for minimizing the cost of running a deadline-constrained large-scale scientific workflow. The approach includes theoretical analyses on resource utilization, DAG simplification, DAG splitting method, and the TOID algorithm for optimal operation pattern. Through rigorous evaluation studies, the proposed approach outperforms existing algorithms in terms of computation and communication cost.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Computer Science, Theory & Methods
Feng Li, Fengguang Song
Summary: Optimizing deployment plans for in-situ workflows in geographically distributed heterogeneous computing environments is challenging. This study presents a heuristic-based solver using the SNL algorithm, which produces effective deployment plans with significantly reduced problem-solving time compared to the CPLEX optimization method.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Fan Liang, Wei Yu, Xing Liu, David Griffith, Nada Golmie
Summary: The Industrial Internet of Things (IIoT) is crucial for connecting IoT devices in industrial settings, enabling operators to control and manage manufacturing systems more efficiently and achieve automation. Efficient processing of different types of applications, especially time-sensitive tasks, is key in IIoT environments. It is important to allocate computing resources effectively to reduce processing times for time-sensitive tasks, while also considering nonpreemptive tasks in IIoT systems.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Xiaoping Li, Dongyuan Pan, Yadi Wang, Ruben Ruiz
Summary: In this paper, a hybrid resource reliability model is constructed to optimize the QoS for tenants in scheduling workflow instances. The model takes into account both cloud resource reliability and precedence constraints in workflows.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Engineering, Chemical
Aroosa Mubeen, Muhammad Ibrahim, Nargis Bibi, Mohammad Baz, Habib Hamam, Omar Cheikhrouhou
Summary: The study introduces an adaptive load-balanced task scheduling algorithm that reduces the makespan, maximizes resource utilization, and adaptively minimizes SLA violation. Compared to other task scheduling methods, the proposed algorithm shows significant improvements in reducing makespan, SLA violation, and resource utilization.
Article
Computer Science, Interdisciplinary Applications
Ge Chen, Junbo Zhang, Mingchao Ning, Wei Cui, Mengcheng Ma
Summary: In order to address the complex task scheduling problem in microservice-oriented industrial software, a scheduling model consisting of a task model and a resource model is established. A task importance function is designed to evaluate the importance of tasks, and a Dynamic Importance-aware Online Scheduling Algorithm (DIOS) is proposed to rank and schedule tasks based on their importance. Furthermore, resource reservation, preemptive scheduling, and online adaptive tuning methods are introduced to enhance the efficiency and adaptability of the DIOS algorithm. Simulation results in two industrial software scenarios demonstrate that the proposed algorithm outperforms widely used algorithms such as First Come First Serve (FCFS), Earliest Deadline First (EDF), Least Laxity First (LLF), and Fixed Priority Scheduling (FPS).
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Zhengyu Yang, Yi Yao, Han Gao, Jiayin Wang, Ningfang Mi, Bo Sheng
Summary: Efficiently managing resources and improving the throughput of large-scale clusters is crucial, especially with the rise of data processing applications. A novel resource allocation scheme named OPERA is proposed to break barriers among resource containers and re-assign resources based on actual utilization, reducing job execution time and improving resource utilization.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2021)
Article
Computer Science, Information Systems
Faisal Ahmad, Mohammad Shahid, Mahfooz Alam, Zubair Ashraf, Mohammad Sajid, Ketan Kotecha, Gaurav Dhiman
Summary: This study investigates the allocation problem of multiple workflows in a cloud environment and proposes a levelized multiple workflow allocation strategy with task merging. The experimental results show that this strategy outperforms its peers in most cases in terms of various performance parameters.
Article
Computer Science, Theory & Methods
Jonathan Bader, Fabian Lehmann, Lauritz Thamsen, Ulf Leser, Odej Kao
Summary: This study presents a method for locally predicting the runtimes of scientific workflow tasks before execution on heterogeneous compute clusters. The method utilizes microbenchmarks and Bayesian linear regression to quickly profile the workflow and provide uncertainty estimates, achieving improved prediction performance compared to existing baselines.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Information Systems
Yujian Zhang, Fei Tong, Chuanyou Li, Yuwei Xu
Summary: The article proposes a memetic algorithm for energy-efficient workflow scheduling, combining a non-dominated sorting genetic algorithm and heuristic methods to achieve quality guarantee and high runtime efficiency. Experimental results show that the algorithm achieves significant energy saving and optimization in workflows from both randomly-generated and real-world applications.
Article
Computer Science, Theory & Methods
Ilia Pietri, Rizos Sakellariou
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Computer Science, Hardware & Architecture
Ewa Deelman, Anirban Mandal, Ming Jiang, Rizos Sakellariou
INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS
(2019)
Article
Automation & Control Systems
Georgios Kourtis, Evangelia Kavakli, Rizos Sakellariou
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2019)
Article
Computer Science, Information Systems
Zeqian Meng, John Brooke, Junyi Han, Rizos Sakellariou
JOURNAL OF GRID COMPUTING
(2020)
Article
Computer Science, Software Engineering
Sukhpal Singh Gill, Shreshth Tuli, Adel Nadjaran Toosi, Felix Cuadrado, Peter Garraghan, Rami Bahsoon, Hanan Lutfiyya, Rizos Sakellariou, Omer Rana, Schahram Dustdar, Rajkumar Buyya
JOURNAL OF SYSTEMS AND SOFTWARE
(2020)
Review
Computer Science, Hardware & Architecture
Ahmad Zareie, Rizos Sakellariou
Summary: Online social networks provide a platform for rapid dissemination of information, but misinformation can also spread quickly, leading to concerns about reliability and trust. Detecting and containing the spread of misinformation has become a key focus in social network analysis.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Abdul Rahman Hummaida, Norman W. Paton, Rizos Sakellariou
Summary: This paper proposes a decentralized reinforcement learning management policy for cloud resource allocation, which can achieve fast convergence and reduce SLA violations compared to centralized architectures.
JOURNAL OF GRID COMPUTING
(2022)
Article
Computer Science, Information Systems
Ahmad Zareie, Rizos Sakellariou
Summary: The paper addresses the challenge of balancing the reduction in infection rate and the cost of social distancing, by treating it as a bi-objective optimization problem. It proposes two methods to dynamically determine the extent of contact restriction during a virus outbreak, which are proven effective in decreasing infection rate and social distancing cost.
SOCIAL NETWORK ANALYSIS AND MINING
(2022)
Article
Computer Science, Software Engineering
Abdul R. Hummaida, Norman W. Paton, Rizos Sakellariou
Summary: The study proposes a hybrid hierarchical decentralized architecture to address issues in cloud infrastructure management, aiming to achieve lower SLA violations and reduce network traffic.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2023)
Article
Computer Science, Information Systems
Ahmad Zareie, Rizos Sakellariou
Summary: Centrality measures are commonly used to capture properties of nodes in a social network, especially in deterministic networks. However, there are models that consider uncertain edges in the calculation of centrality. In this paper, a fuzzy graph model is proposed to capture the uncertainty in social networks, and fuzzy centrality measures are introduced. Experimental results show that these measures accurately determine node importance in fuzzy graphs compared to other fuzzy or deterministic centrality measures.
INFORMATION SYSTEMS
(2023)
Proceedings Paper
Computer Science, Hardware & Architecture
Petar Kochovski, Rizos Sakellariou, Marko Bajec, Pavel Drobintsev, Vlado Stankovski
2019 IEEE 33RD INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Evangelia Kavakli, Jorge Buenabad-Chavez, Vasilios Tountopoulos, Pericles Loucopoulos, Rizos Sakellariou
2018 IEEE INTERNATIONAL CONFERENCE ON SMART COMPUTING (SMARTCOMP 2018)
(2018)
Proceedings Paper
Computer Science, Hardware & Architecture
Mingze Ma, Rizos Sakellariou
PARMA-DITAM 2018: 9TH WORKSHOP ON PARALLEL PROGRAMMING AND RUNTIME MANAGEMENT TECHNIQUES FOR MANY-CORE ARCHITECTURES AND 7TH WORKSHOP ON DESIGN TOOLS AND ARCHITECTURES FOR MULTICORE EMBEDDED COMPUTING PLATFORMS
(2018)
Proceedings Paper
Computer Science, Information Systems
Jorge Buenabad-Chavez, Gabor Kecskemeti, Vasilios Tountopoulos, Evangelia Kavakli, Rizos Sakellariou
2018 SIXTH INTERNATIONAL CONFERENCE ON ENTERPRISE SYSTEMS (ES 2018)
(2018)
Proceedings Paper
Computer Science, Information Systems
Evangelia Kavakli, Jorge Buenabad-Chavez, Vasilios Tountopoulos, Pericles Loucopoulos, Rizos Sakellariou
2018 SIXTH INTERNATIONAL CONFERENCE ON ENTERPRISE SYSTEMS (ES 2018)
(2018)
