Article
Computer Science, Information Systems
Eyhab Al-Masri, Alireza Souri, Habiba Mohamed, Wenjun Yang, James Olmsted, Olivera Kotevska
Summary: This article proposes a cooperative energy-aware resource allocation and scheduling strategy based on the TOPSIS multi-criteria decision-making method. The method achieves load balancing by allocating and scheduling virtual machine resources and considers energy efficiency as an optimization objective. Experimental results show that the proposed approach outperforms existing algorithms in terms of energy savings and execution time.
INTERNET OF THINGS
(2023)
Article
Computer Science, Hardware & Architecture
Hamidreza Mahini, Amir Masoud Rahmani, Seyyedeh Mobarakeh Mousavirad
Summary: The research addresses the IoT task offloading challenge by preparing a set of Python tasks for evaluation, proposing a four-tier architecture for decision-making, formulating the problem as an evolutionary game, and simulating the scheme in MATLAB. The proposed approach contributes to core traffic decreases and has a convergence time of less than 6 seconds for solving problems with 100 tasks.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Computer Science, Information Systems
Masoud Nematollahi, Ali Ghaffari, A. Mirzaei
Summary: The Internet of Things (IoT) technology is widely used in areas such as intelligent healthcare systems and virtual reality applications. Cloud services are commonly used to overcome the processing power limitations of IoT devices, but they suffer from issues such as high latency, high traffic, and high energy consumption. This study presents a novel architecture that implements Fog Computing (FC) in the IoT to address these concerns and optimize resource distribution using blockchain advantages.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Benyamin T. Tabarsi, Ali Rezaee, Ali Movaghar
Summary: Fog computing is an important research topic for optimizing latency and power consumption through partial computation offloading and resource allocation in the context of IoT. This scheme maximizes the utilization of fog layer capacity, reduces power consumption in end-user layer, improves system reliability, and handles user requests effectively.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Saif Aljanabi, Abdolah Chalechale
Summary: With the rapid development of IoT devices and applications, the necessity of providing high processing capabilities becomes crucial. To address the issue of running complex applications, a hybrid fog-cloud offloading (HFCO) method is introduced, where tasks can be offloaded to cloud servers or nearby fog nodes for more efficient execution.
Article
Computer Science, Information Systems
Habiba Mohamed, Eyhab Al-Masri, Olivera Kotevska, Alireza Souri
Summary: This paper proposes OpERA, a multi-layered edge-based resource allocation optimization framework that supports heterogeneous edge devices. It optimizes resource allocation by capturing offloadable task requirements, reducing costs and energy consumption, and increasing the likelihood of successful task offloading.
Article
Chemistry, Analytical
Usman Mahmood Malik, Muhammad Awais Javed, Jaroslav Frnda, Jan Rozhon, Wali Ullah Khan
Summary: This paper discusses the importance of fog computing in future 6G networks and presents a parallel task offloading algorithm based on many-to-one matching. By developing preference profiles and addressing externalities, the algorithm reduces task computation delay and improves system performance.
Article
Computer Science, Theory & Methods
Hoa Tran-Dang, Dong-Seong Kim
Summary: This article introduces a framework called FRATO for minimizing service provisioning delay in IoT-fog-cloud systems through an adaptive task offloading mechanism. FRATO is based on fog resource to flexibly select the optimal offloading policy, including a collaborative task offloading solution based on the data fragment concept. Through simulation analysis, the method shows potential advantages in significantly reducing average delay in systems with high rate of service requests and heterogeneous fog environment.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Amira S. Ibrahim, Hassan Al -Mahdi, Hamed Nassar
Summary: Fog computing improves the quality of service/experience in IoT by bringing cloud resources closer to terminal devices. A novel scheme is proposed to determine task offloading based on computational needs. A queueing theoretic model is developed to optimize offloading performance.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Wanli Yu, Ardalan Najafi, Yanqiu Huang, Alberto Garcia-Ortiz
Summary: The study aimed to address the gap of task allocation approaches that do not consider approximate computing, proposing a method that simultaneously considers approximate computing and task allocation to maximize network lifetime. By allocating tasks and selecting execution modes, a centralized and distributed algorithm were proposed to solve the problem for resource-limited IoT devices, with the distributed algorithm achieving comparable results to the centralized one and outperforming previous approaches.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Sudip Misra, Pramodh Rachuri, Pallav Kumar Deb, Anandarup Mukherjee
Summary: In IoT environments, hard real-time tasks with fixed deadlines are executed with the help of cloud and fog computing platforms to facilitate task allocation and execution among IoT sensor nodes. By breaking down tasks into smaller subtasks and offloading them to nearby fog nodes using a greedy approach, operational latencies can be reduced effectively. The online learning D2CIT scheme enables parallel execution of subtasks to reduce latency and improve efficiency, offering a 17% reduction in latency and a 59% speedup compared to traditional fog computing schemes and existing online learning-based task offloading solutions.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Mohammad Aknan, Maheshwari Prasad Singh, Rajeev Arya
Summary: The role of IoT applications has become increasingly important in various fields, but also brings a large amount of data and a range of challenges. To address these challenges, we propose a Blockchain-enabled Intelligent framework that integrates AI-based meta-heuristic algorithm to allocate optimal resources for IoT requests, improve result quality, and ensure the security of IoT applications and data.
JOURNAL OF GRID COMPUTING
(2023)
Article
Computer Science, Information Systems
Maryam Sheikh Sofla, Mostafa Haghi Kashani, Ebrahim Mahdipour, Reza Faghih Mirzaee
Summary: This paper evaluates fog offloading mechanisms, discusses current and future trends, categorizes different types of offloading mechanisms, analyzes the pros and cons of each mechanism, and provides a reference for addressing offloading issues in fog computing.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Xiaojian Zhu, MengChu Zhou
Summary: Mobile-edge computing reduces workload and network delay by deploying computational resources near devices, focusing on user experience and cost reduction for service providers. Research on joint cloudlet deployment and task offloading aims to minimize energy consumption, task response delay, and deployed cloudlets, using a modified optimization algorithm to find tradeoff solutions. The algorithm's superiority is confirmed through extensive simulations.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Mohammad Aazam, Saif ul Islam, Salman Tariq Lone, Assad Abbas
Summary: This paper presents a three-tier IoT-fog-cloud model that aims to achieve high scalability of IoT services and manage global energy consumption through distributed task execution. The study evaluates the performance based on various application scenarios, using real datasets and considering fog-only, cloud-only, and fog-cloud collaborative scenarios. Task execution policy plays a key role in efficiently processing tasks, especially in deep learning, and the types of policies suitable for different offloading environments are elaborated upon.
IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING
(2022)
Article
Telecommunications
Samira Esfandiari, Mohammad Hossein Rezvani
Summary: Disruption-tolerance networks (DTNs) are suitable for applications with intermittent network connectivity. Incentives and rewarding mechanisms are needed to motivate relay nodes to share resources and improve routing functionality. Microeconomics theories are used to model interactions between DTN nodes and create incentives for cooperation.
TELECOMMUNICATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Maryam Keshavarznejad, Mohammad Hossein Rezvani, Sepideh Adabi
Summary: In the past two decades, efficiency of mobile applications has increased significantly, but task offloading may not be the best option for delay-sensitive applications. Fog computing serves as a complementary solution by bringing computing resources closer to mobile devices, yet is limited by scarce computing resources. To reduce response delays to mobile user requests, a trade-off between local execution on end-devices and fog environment is crucial.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Reza Besharati, Mohammad Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi
Summary: This paper proposes a second-price sealed-bid auction mechanism to motivate fog nodes to participate in task offloading operations and uses queuing theory for resource allocation in the edge layer and the cloud layer. Experimental evaluations show that the proposed method outperforms other methods in terms of execution time, energy consumption, and network usage.
JOURNAL OF GRID COMPUTING
(2021)
Article
Telecommunications
Amir Babazadeh Nanehkaran, Mohammad Hossein Rezvani
Summary: The paper introduces an auction mechanism to incentivize node cooperation in forwarding messages in Delay Tolerant Networks. Simulation results demonstrate that the proposed method enhances network performance under moderate and intense traffic conditions by improving delivery ratio, reducing average buffer usage, and overhead.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Mohammad Hassan Khoobkar, Mehdi Dehghan Takht Fooladi, Mohammad Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi
Summary: The use of fog computing is increasing in delay-sensitive applications. This paper proposes a partial offloading method based on replicator dynamics of evolutionary game theory, which improves performance and reduces energy consumption and latency. The method does not require hidden information from other users.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Zahra Ghafouri-ghomi, Mohammad Hossein Rezvani
Summary: This paper proposes a method inspired by the Landlord-Peasants game to increase collaboration between selfish nodes in disruption-tolerant networks. The simulation results show that the proposed method outperforms baseline methods and a state-of-the-art learning-based method in terms of delivery ratio, buffer usage, and number of hops, with a comparable overhead.
Article
Computer Science, Software Engineering
Mohammad Hossein Ghasemian Koochaksaraei, Abolfazl Toroghi Haghighat, Mohammad Hossein Rezvani
Summary: This article presents an auction-inspired model for resource exchange among cloud service providers (CSPs) without using monetary values. The proposed mechanism enhances CSPs' social welfare and profitability while significantly reducing SLA violations. Additionally, the model satisfies essential economic properties, such as individual rationality, incentive compatibility, budget balancing, and economic efficiency.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Tahereh Abbasi-khazaei, Mohammad Hossein Rezvani
Summary: This study proposes a virtual machine placement method to jointly minimize energy costs and scheduling, aiming to address the critical concerns of cloud service providers. The performance of the algorithm is compared with baseline methods and the simulation results demonstrate its effectiveness.
Article
Mathematics, Interdisciplinary Applications
Reza Besharati, Mohammad Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi
Summary: In the fog computing paradigm, tasks can be offloaded to nearby devices or the central cloud if the computing resources of an end device are insufficient. This paper proposes a bid prediction mechanism using Q-learning based on the auction theory for optimal offloading. The evaluation results show that the predicted bid values by the Q-learning method are near-optimal, consuming less energy and reducing execution time of tasks.
Article
Computer Science, Artificial Intelligence
Alireza Abdolmaleki, Mohammad Hossein Rezvani
Summary: This paper explores how to optimize the efficiency of movie recommender systems by using a combination of genetic algorithm and content-based filtering methods to adjust the weights of contextual information, leading to improvements in accuracy and recommendation rates.
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mohammad Hassan Khoobkar, Mehdi Dehghan Takht Fooladi, Mohammad Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi
Summary: Partial offloading is crucial in fog/cloud computing due to the increasing demand for delay-sensitive applications. However, traditional game-theoretical models suffer from scalability problems and overlook the dynamic changes in the fog environment. This paper proposes a dual-population modeling approach using replicator dynamics to efficiently capture the growing/shrinking behavior of CPU cycles on both the user and network sides, yielding superior results compared to existing methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Computer Science, Information Systems
Sanaz Taheri-abed, Amir Masoud Eftekhari Moghadam, Mohammad Hossein Rezvani
Summary: Mobile Cloud Computing (MCC) is no longer sufficient to handle the increasing data volume and real-time application delays. Challenges such as security, energy consumption, storage space, bandwidth, mobility support, and location awareness have made this problem more complex. Edge Computing (MEC) and Fog Computing (FC) are critical techniques for the IoT, and machine learning-based computation offloading mechanisms in these environments are reviewed in this paper.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Omid Soleiman-garmabaki, Mohammad Hossein Rezvani
Summary: This paper examines the factors affecting customer churn in the telecom industry and analyzes them using various data mining classification methods. By evaluating different criteria, this paper demonstrates the trade-off between speed and accuracy in hybrid classifiers and proposes a more accurate combined classification method.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Software Engineering
Tayebeh Sadat Mousavi, Achyut Shankar, Mohammad Hossein Rezvani, Hamid Ghadiri
Summary: In this paper, an entropy-based method is proposed for virtual machine placement (VMP) on specialized physical hosts. The method aims to minimize entropy by considering the type of VMs, using the Gini coefficient as the entropy criterion. The non-dominated sorting genetic algorithm (NSGA-III) is employed to solve the multi-objective problem, and the combination with differential evolution methods enhances the solution quality. Simulation results on the CloudSim simulator demonstrate that the entropy-based method outperforms existing methods in terms of utilization, resource wastage, and energy consumption.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Mona Naghdehforoushha, Mehdi Dehghan Takht Fooladi, Mohammad Hossein Rezvani, Mohammad Mehdi Gilanian Sadeghi
Summary: This paper discusses the trading of computing services in the cloud computing market, focusing on the Amazon spot market and the challenges users face. It proposes a method called bi-level Markov decision-making process (BLMDP) to jointly minimize the cost of processing tasks and maximize user satisfaction. Performance evaluation shows that BLMDP outperforms heuristic methods in minimizing cloud provider costs and maximizing user gain.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
(2022)