Search

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the proliferation in the internet of things (IoT), a variety of delay sensitive applications have emerged over the past few years. Fog computing acts a viable computing paradigm for meeting the requirements of IoT applications. However, heterogeneous IoT tasks, resource constrained fog nodes makes task scheduling a challenging task. Efficient task scheduling reduces the computation cost, latency, energy and enhances the utilization of resources. In this paper, we propose the improved version of the meta-heuristic algorithm spider monkey optimization (SMO). We propose greedy task scheduling SMO (gTS-SMO) and semi-greedy task scheduling SMO (sgTS-SMO) for efficient task scheduling in fog computing environment. The main aim is minimize delay and energy consumption while considering the constraints of deadline and violation time. The system is evaluated based on the parameters of deadline violation time, makespan, energy consumption, total cost, and degree of imbalance. The results shows gTS-SMO reduces the violation time by 13.86%, 88.38% on comparison with sgTS-SMO and particle swarm optimization (PSO) respectively. The results also depicts the outperformance of gTS-SMO in terms of makespan and energy consumption. Makespan is reduced by 6.28%, and 57.75% and energy consumption by 5.74% and 53.65% on comparison with sgTS-SMO and PSO respectively. [ABSTRACT FROM AUTHOR]

The rapid growth of service-oriented and cloud computing has created large-scale data centres worldwide.Modern data centres’ operating costs mostly come from back-end cloud infrastructure and energy consumption. In cloud computing, extensive communication resources are required.Moreover, cloud applications requiremore bandwidth to transfer large amounts of data to satisfy end-user requirements. It is also essential that no communication source can cause congestion or bag loss owing to unnecessary switching buffers. This paper proposes a novel Energy and Communication (EC) aware scheduling (EC-scheduler) algorithm for green cloud computing, which optimizes data centre energy consumption and traffic load. The primary goal of the proposed EC-scheduler is to assign user applications to cloud data centre resources with minimal utilization of data centres. We first introduce a Multi-Objective Leader Salp Swarm (MLSS) algorithm for task sorting, which ensures traffic load balancing, and then an Emotional Artificial Neural Network (EANN) for efficient resource allocation. EC-scheduler schedules cloud user requirements to the cloud server by optimizing both energy and communication delay, which supports the lower emission of carbon dioxide by the cloud server system, enabling a green, unalloyed environment. We tested the proposed plan and existing cloud scheduling methods using the GreenCloud simulator to analyze the efficiency of optimizing data centre energy and other schedulermetrics. The EC-scheduler parameters PowerUsage Effectiveness (PUE), Data Centre Energy Productivity (DCEP), Throughput, Average Execution Time (AET), Energy Consumption, and Makespan showed up to 26.738%, 37.59%, 50%, 4.34%, 34.2%, and 33.54% higher efficiency, respectively, than existing state of the art schedulers concerning number of user applications and number of user requests. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) has become a significant issue in designing smart cities. Many applications and services are provided in IoV for various purposes. They need the resources for the computation and data collection. One of the open issues in IoV is resource management because of resource limitation, resource heterogeneity, and dynamic networks. To our knowledge, no systematic and thorough research in resource management methodologies was conducted in IoV, despite the critical nature of resource management challenges. This paper analyzes the recently published studies on resource management in IoV. Our analysis shows that resource allocation has the most utilization rate of resource management approaches at 30%. The most critical parameter in resource allocation is cost, which includes energy, time, price, and processing capacity. The analytical reports show those cost parameters have the most evaluation in the approaches by 19%. Furthermore, we propose a taxonomy for resource management in IoV and extract challenges and open issues in this field. It can be a start point to suggest new methods for resource management in IoV. [ABSTRACT FROM AUTHOR]

Summary: Task scheduling is a critical problem in the cloud computing environment since it has a significant impact on the system's performance. Security and robust based task allocation model improves the security of real‐time solicitations whereas preserving a high‐level performance of the data center. Here, to minimize the makespan in task allocation existing research proposed a bio‐inspired algorithm in a multi‐cloud environment, but, it needs more memory to update velocity and increases the processing time. Therefore, this research proposed a Machine Learning based Secure and Efficient Task Allocation in Multi‐Cloud Environment. First, the proposed model has a task classifier module that categorizes the matching it to the appropriate VM type for the task that was submitted. The next is the task allocation module, in which, an Intellectual Gravitational Search‐Genetic Algorithm is suggested to allocate the task to a VM. The tasks are distributed to the VMs in the order specified after the allocating phase in which they will be executed. Finally, to secure the task allocation in multi‐cloud, this research proposed a Naïve Bayes module to detect the attacks. The models and experimental findings demonstrate that our proposed approach produces a shorter makespan, lower cost, improved resource utilization, and better trade‐off between time and economic cost. It is more dependable and effective in multi‐cloud environment. [ABSTRACT FROM AUTHOR]

The significant energy consumption within data centers is an essential contributor to global energy consumption and carbon emissions. Therefore, reducing energy consumption and carbon emissions in data centers plays a crucial role in sustainable development. Traditional cloud computing has reached a bottleneck, primarily due to high energy consumption. The emerging federated cloud approach can reduce the energy consumption and carbon emissions of cloud data centers by leveraging the geographical differences of multiple cloud data centers in a federated cloud. In this paper, we propose Eco-friendly Reinforcement Learning in Federated Cloud (ERLFC), a framework that uses reinforcement learning for task scheduling in a federated cloud environment. ERLFC aims to intelligently consider the state of each data center and effectively harness the variations in energy and carbon emission ratios across geographically distributed cloud data centers in the federated cloud. We build ERLFC using Actor-Critic algorithm, which select the appropriate data center to assign a task based on various factors such as energy consumption, cooling method, waiting time of the task, energy type, emission ratio, and total energy consumption of the current cloud data center and the details of the next task. To demonstrate the effectiveness of ERLFC, we conducted simulations based on real-world task execution data, and the results show that ERLFC can effectively reduce energy consumption and emissions during task execution. In comparison to Round Robin, Random, SO, and GJO algorithms, ERLFC achieves respective reductions of 1.09, 1.08, 1.21, and 1.26 times in terms of energy saving and emission reduction. [ABSTRACT FROM AUTHOR]

Task scheduling (TS) in cloud computing is a complex problem that involves balancing workload distribution, resource allocation, and power consumption. Existing methods often fail to optimize these objectives simultaneously and efficiently. This paper introduces a novel technique for scheduling independent tasks in cloud computing using multi-objective optimization and deep reinforcement learning (DRL). The proposed technique, DMOTS-DRL, combines Dueling deep Q-networks and dynamic prioritized experience replay to optimize two critical objectives: scheduling completion time (makespan) and power consumption. The performance of DMOTS-DRL is evaluated using CloudSim and compared with several state-of-the-art TS algorithms. The experimental results show that DMOTS-DRL outperforms the other algorithms in reducing makespan, power consumption, and other metrics, demonstrating its effectiveness and reliability for cloud computing services. Specifically, DMOTS-DRL achieves percentage improvements ranging from − 44.04 to − 0.19% in makespan, from − 0.26 to − 27.90% in power consumption, as well as better performance on other metrics such as energy consumption, degree of imbalance, resource utilization, and average waiting time. [ABSTRACT FROM AUTHOR]

Edge–fog–cloud computing system can be divided into edge or IoT layer (tier 1), fog layer (tier 2) and cloud layer (tier 3). The devices at the edge layer generate different types of tasks which may be computation-intensive or communication intensive or having a combination of these properties. Depending on the characteristics of tasks, those may be scheduled to run at the edge or fog or cloud layers. There are many advantages of offloading some of the computationally intensive workloads, which includes improved response time, satisfying the deadlines of delay-sensitive tasks and overall reduced make span of the workloads. In this context, there is a need for designing a scheduling algorithm with the goal to minimize the overall execution time while satisfying the deadlines of the tasks and maximizing the resource utilization at fog layer. In this paper, we are proposing a task offloading and scheduling algorithm based on the osmotic approach. In the osmotic approach, the devices and tasks are classified, and the tasks are assigned to the most suitable devices based on their dynamically available capacity. The proposed scheduling algorithm is compared with traditional random task offloading and round robin task offloading algorithms using synthetic data sets and found that the proposed algorithm performance is significantly better than other algorithms. [ABSTRACT FROM AUTHOR]

The advancement of Industrial Internet of Things (IIoT) applications has increased the demand for efficient and energy-aware task scheduling in fog-cloud environments. This paper presents a novel multi-objective energy efficient task scheduling based reinforcement learning (MEETS-RL) model for fog-cloud IIoT-based systems. The IIoT, fog, and cloud are the three layers obtained in the proposed method. Tasks are captured from various industries through industrial devices such as actuators, sensors, and control systems placed near fog nodes. The task classification stage utilizes the ID3 algorithm to classify tasks based on their priority, Quality of Service (QoS), and processing requirements. After classification, appropriate fog nodes are selected for task execution considering factors such as energy consumption, processing capabilities, and proximity to IIoT devices. The unhandled task in fog nodes is offloaded to cloud data centers using the first fit (FF) algorithm, based on available resources, QoS requirements, and fog node location. Once the suitable fog nodes or cloud data centers have been identified, the tasks are scheduled for execution using a reinforcement learning-based task scheduling algorithm. Experimental evaluations demonstrate that the proposed MEETS-RL model outperforms existing task scheduling models, including first come first serve (FCFS), greedy for energy (GfE), shortest job first (SJF), round Robin (RR), and Laxity based priority with Ant colony system (LBP-ACS). The experimental results of the proposed architecture showed an accuracy rate of 98.8%, task completion rate of 95% and energy consumption of 0.4 J. The proposed architecture offers a comprehensive solution for modern IIoT systems demanding flexibility, scalability, and efficient resource management while enhancing energy efficiency through the application of reinforcement learning in task scheduling. [ABSTRACT FROM AUTHOR]

In cloud computing, optimizing task scheduling is crucial for improving overall system performance and resource utilization. To minimize cloud service costs and prevent resource wastage, advanced techniques must be employed to efficiently allocate cloud resources for executing tasks. This research presents a novel multi-objective task scheduling method, BSSA, which combines the Backtracking Search Optimization Algorithm (BSA) and the Sparrow Search Algorithm (SSA). BSA enhances SSA's convergence accuracy and global optimization ability in later iterations, improving task scheduling results. The proposed BSSA is evaluated and compared against traditional SSA and other algorithms using a set of 8 benchmark test functions. Moreover, BSSA is tested for task scheduling in cloud environments and compared with various metaheuristic scheduling algorithms. Experimental results demonstrate the superiority of the proposed BSSA, validating its effectiveness and efficiency in cloud task scheduling. [ABSTRACT FROM AUTHOR]

The article introduces a cost-based data prefetching and task scheduling framework in Big Data platforms over underlying tiered storage system. Topics discussed include solutions to task scheduling, resource scheduling and data prefetching problems over tiered storage, pruning algorithms for reducing scheduling time, YARN cluster resource request model, storage-tier-aware task scheduling approach, and implementation of Trident scheduling and prefetching components in Apache Hadoop and Spark.

In order to realize the intelligence of the radio and television transmission station automatic control system, the intelligent algorithm is used for the dynamic task scheduling of transmission (DTST) and the intelligent generation of the real-time transmission schedule. On the basis of the static task allocation at the same time, the time dimension is introduced to build a dynamic task scheduling mathematical model. Based on the characteristics of simple operation and strong convergence of the genetic algorithm, an improved genetic algorithm (IGA) is proposed to solve DTST. The algorithm is improved for specific problems. The first is to improve the selection operator based on the elitist retention strategy to improve the convergence of the algorithm; the second is to determine the discontinuous crossover genes frag based on the concept of cyclic replacement sequence to improve the crossover operator, so as to retain the complete excellent gene fragments and improve the computational efficiency of the crossover operator; the third is to design the relative swap mutation operator to increase the diversity of the population and avoid the convergence of the algorithm calculation results to the local optimal solution. Through the analysis of the experimental data of traversing parameters, the optimal parameter configuration of the IGA is obtained. Finally, the correctness of the IGA is verified by comparing it with the enumeration algorithm, and the effectiveness of the IGA is verified by comparing it with the greedy algorithm. [ABSTRACT FROM AUTHOR]

Due to the problem of large latency and energy consumption of fog computing in smart community applications, the fog computing task-scheduling method based on Hybrid Ant Lion Optimizer (HALO) is proposed in this paper. This method is based on the Ant Lion Optimizer (ALO. Firstly, chaotic mapping is adopted to initialize the population, and the quality of the initial population is improved; secondly, the Adaptive Random Wandering (ARW) method is designed to improve the solution efficiency; finally, the improved Dynamic Opposite Learning Crossover (DOLC) strategy is embedded in the generation-hopping stage of the ALO to enrich the diversity of the population and improve the optimization-seeking ability of ALO. HALO is used to optimize the scheduling scheme of fog computing tasks. The simulation experiments are conducted under different data task volumes, compared with several other task scheduling algorithms such as the original algorithm of ALO, Genetic Algorithm (GA), Whale Optimizer Algorithm (WOA) and Salp Swarm Algorithm (SSA). HALO has good initial population quality, fast convergence speed, and high optimization-seeking accuracy. The scheduling scheme obtained by the proposed method in this paper can effectively reduce the latency of the system and reduce the energy consumption of the system. [ABSTRACT FROM AUTHOR]

Nowadays, multi-access edge computing (MEC) has been widely recognized as a promising technology that can support a wide range of new applications for the Internet of Things (IoT). In dynamic MEC networks, the heterogeneous computation capacities of the edge servers and the diversified requirements of the IoT applications are both asymmetric, where and when to offload and schedule the time-dependent tasks of IoT applications remains a challenge. In this paper, we propose a flexible offloading and task scheduling scheme (FLOATS) to adaptively optimize the computation of offloading decisions and scheduling priority sequences for time-dependent tasks in dynamic networks. We model the dynamic optimization problem as a multi-objective combinatorial optimization problem in an infinite time horizon, which is intractable to solve. To address this, a rolling-horizon-based optimization mechanism is designed to decompose the dynamic optimization problem into a series of static sub-problems. A genetic algorithm (GA)-based computation offloading and task scheduling algorithm is proposed for each static sub-problem. This algorithm encodes feasible solutions into two-layer chromosomes, and the optimal solution can be obtained through chromosome selection, crossover and mutation operations. The simulation results demonstrate that the proposed scheme can effectively reduce network costs in comparison to other reference schemes. [ABSTRACT FROM AUTHOR]

In software defined networks (SDN), the controller deployment solution directly affects the service quality of SDN. A multi-controller deployment algorithm based on network partition (MCDNP) is proposed by integrating the idea of a genetic algorithm with a time latency to be the optimization target, which divides the network firstly, then calculates the web's time latency, and finally decides the deployment location. Experiments based on OS3E networks show that the MCDNP algorithm effectively reduces the latency. In addition, for the collaborative task scheduling problem based on task dependency relationship, this paper also proposes a collaborative task scheduling algorithm based on dependency relationship (CTSSR) in which the optimization goal is to minimize the mean power loss of tasks while guaranteeing the system QoS. The CTSSR algorithm considers the task dependency model to ensure the dependency constraints in task execution. The CTSSR algorithm prioritizes the tasks with the shortest scheduling time and the dependency constraints for scheduling and considers the power usage of the edge server during scheduling. The experiment indicates that the CTSSR algorithm effectively decreases the duration for task completion and the energy consumption of the edge base station. [ABSTRACT FROM AUTHOR]

The scheduling of applications is one of the prominent challenges in cloud computing, due to run time mapping by task scheduler between upcoming workload and cloud resources. An efficient scheduling algorithm is needed to schedule the diverse workload and improve the performance metrics by minimizing makespan and maximizing resource utilization. Many of the existing scheduling techniques addressed only makespan and resource utilization parameters and did not consider some other significant parameters like Energy consumption, migration time etc. that directly impacts the performance of cloud services. To overcome the mentioned issues, authors have proposed a nature inspired multi-objective task scheduling Grey wolf optimization (MOTSGWO) algorithm that has the ability to take the scheduling decision at runtime based upon the status of cloud resources and upcoming workload demands. In addition, the proposed technique allocates the resources based upon the budget of end users as well as priorities of tasks. The proposed MOTSGWO approach implemented on Cloudsim toolkit and the workload is generated by creation of datasets (da01, da02, da03, da04) with different distributions of tasks and workload traces taken from HPC2N and NASA (da05, da06) parallel workload archives. The results of extensive experiment shows that the proposed MOTSGWO approach outperforms other baseline policies and improved the significant parameters. [ABSTRACT FROM AUTHOR]

Container virtualization technology represented by Docker has been widely used in the industry due to its advantages of lightweight, fast deployment, and easy portability. This paper considers the scenarios of AI-based IoT applications based on container technology in a cloud-edge collaborative environment, and proposes a container-based task scheduling algorithm. Using priority-aware greedy strategy, a new scheduling algorithm named PGT has been proposed which adopts the multi-criteria approach Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The containers in cloud servers and edge servers are managed in a uniform platform, and IoT application services are deployed in containers. The task with smaller deadline constraint is scheduled first due to its higher priority. Then, multiple indicators are considered comprehensively, such as task response time, energy consumption, task execution cost, to find the optimal container to execute task. Through varying the number of edge servers and the number of tasks, the simulation results in a cloud-edge collaborative environment indicate that the proposed scheduling approach outperforms the four baseline algorithms in improving QoS satisfaction rate, energy consumption, penalty cost and total violation time. [ABSTRACT FROM AUTHOR]

Software as a service (SaaS) provider hires resources from an Infrastructure as a Service (IaaS) provider and provides these sharable resources to user's applications on lease. However, it is becoming a more challenging issue for SaaS providers to meet user's Quality of Service (QoS) Parameter and maximize profit from cloud infrastructure. This proposed work satisfies both the user and the service provider by fulfilling service level agreement (SLA), user's QoS requirement, and increasing profit with efficient resources utilization. This paper proposes an Improved Quantum Salp Swarm Algorithm (IQSSA), which improves the Salp Swarm algorithm by incorporating the principles of Quantum computing to increase the convergence rate. Further, Quantum-inspired Salp Swarm Grey Wolf Algorithm (QSSGWA) embeds SSA with Grey Wolf Optimizer (GWO) to improve the global optimum solution, and quantum operator is used to initializing population. Proposed algorithms execute tasks under the user-defined deadline and budget constraints. Furthermore, the penalty cost is formulated and applied in the case of a deadline violation. IQSSA and QSSGWA are tested on 19 global benchmark functions, and results prove their superior performance compared to SSA, GWO, BAT, and Particle Swarm Optimization (PSO) algorithm. Furthermore, these algorithms are simulated on CloudSim, and performance matrices such as service provider's profit, makespan, SLA violation rate, task rejection rate, throughput, resource utilization, and response time are compared. The comparison analysis demonstrates that the proposed algorithms offer better performance and more efficient scheduling than existing metaheuristics. Furthermore, simulation results clearly show that QSSGWA gives the best results for all performance matrices. This proposed approach can be applied in many scientific domains, where distributed processing of data or large scale data analysis is required such as distributed and federated machine learning, serverless computing, medical applications, etc. [ABSTRACT FROM AUTHOR]

With the continuous integration of IoT technology and information technology, edge computing, as an emerging computing paradigm, makes full use of terminals to process and analyse real-time data. The explosion of Internet of Things (IoT) devices has created challenges for traditional cloud-based data processing models due to high latency and availability requirements. This paper proposes a new edge computation-based framework for iot data processing and scheduling using deep reinforcement learning. The system architecture incorporates distributed iot data access, realtime processing, and an intelligent scheduler based on Deep q networks (DQN). A large number of experiments show that compared with traditional scheduling methods, the average task completion time is reduced by 20% and resource utilization is increased by 15%. The unique integration of edge computing and deep reinforcement learning provides a flexible and efficient platform for lowlatency iot applications. Key results obtained from testing the proposed system, such as reduced task completion time and increased resource utilization. [ABSTRACT FROM AUTHOR]

Domain-specific systems on chip (DSSoCs) aim to narrow the gap between general-purpose processors and application-specific designs. CPU clusters enable programmability, whereas hardware accelerators tailored to the target domain minimize task execution times and power consumption. Traditional operating system (OS) schedulers can diminish the potential of DSSoCs, as their execution times can be orders of magnitude larger than the task execution time. To address this problem, we propose a dynamic adaptive scheduling (DAS) framework that combines the advantages of a fast, low-overhead scheduler and a sophisticated, high-performance scheduler with a larger overhead. We present a novel runtime classifier that chooses the better scheduler type as a function of the system workload, leading to improved system performance and energy-delay product (EDP). Experiments with five real-world streaming applications indicate that DAS consistently outperforms fast, low-overhead, and slow, sophisticated schedulers. DAS achieves a 1.29× speedup and a 45% lower EDP than the sophisticated scheduler under low data rates and a 1.28× speedup and a 37% lower EDP than the fast scheduler when the workload complexity increases. Furthermore, we demonstrate that the superior performance of the DAS framework also applies to hardware platforms, with up to a 48% and 52% reduction in the execution time and EDP, respectively. [ABSTRACT FROM AUTHOR]

Several toolkits are in use to execute cloud applications for technology development. Workflow Sim Toolkit is one of them. It captures the flow of work in a systematic manner and carries out the technical work successfully. To represent and apply the technology, the researchers raised the cloud. For processing technical tasks, cloud service is sustainable to operate with ease of delivery. With dynamic requirements mapping the available resources to ensure tremendous performance, cloud comes into play. By proposing descriptive steps of an algorithm, advanced architecture is able to solve real dynamic complex technical task applications. The suggested architecture is implemented in a real environment with the mentioned toolkit. The proposed architecture is evaluated using the existing work request and Amazon EC2 pricing model. This model gained attention for the most commonly used application by incorporating previous implemented models to predict accuracy in results with actual platform comparisons. In the experimental results of the designed paper, the Approachable Algorithm (AA) got better performance than the basic algorithms i.e. FCFS, RR, MIN-MIN, MAX–MIN and HoneyBees. [ABSTRACT FROM AUTHOR]

Health monitoring systems (HMS) with wearable IoT devices are constantly being developed and improved. But most of these gadgets have limited energy and processing power due to resource constraints. Mobile edge computing (MEC) must be used to analyze the HMS information to decrease bandwidth usage and increase reaction times for applications that depend on latency and require intense computation. To achieve these needs while considering emergencies under HMS, this work offers an effective task planning and allocation of resources mechanism in MEC. Utilizing the Software Denied Network (SDN) framework; we provide a priority-aware semi-greedy with genetic algorithm (PSG-GA) method. It prioritizes tasks differently by considering their emergencies, calculated concerning the data collected from a patient’s smart wearable devices. The process can determine whether a job must be completed domestically at the hospital workstations (HW) or in the cloud. The goal is to minimize both the bandwidth cost and the overall task processing time. Existing techniques were compared to the proposed SD-PSGA regarding average latency, job scheduling effectiveness, execution duration, bandwidth consumption, CPU utilization, and power usage. The testing results are encouraging since SD-PSGA can handle emergencies and fulfill the task’s latency-sensitive requirements at a lower bandwidth cost. The accuracy of testing model achieves 97 to 98% for nearly 200 tasks. [ABSTRACT FROM AUTHOR]

Cloud enterprises are currently facing difficulties managing the enormous amount of data and varied resources in the cloud because of the explosive expansion of the cloud computing system with numerous clients, ranging from small business owners to large corporations. Cloud computing’s performance may need more effective resource planning. Resources must be distributed equally among all relevant stakeholders to maintain the group’s profit and the satisfaction of its consumers. Since these essential resources are unavailable on the board, a client request cannot be put on hold forever. To address these issues, a hybrid machine learning technique for resource allocation security with effective task scheduling in cloud computing is proposed in this study. Initially, a short scheduler for tasks built around the enhanced Particle Swarm Optimization algorithm (IPSO-TS) reduces make-span time and increases throughput. Next, bandwidth and resource load are included in a Graph Attention Neural Network (GANN) for effective resource allocation under various design limitations. Finally, NSUPREME, a simple identification technique, is suggested for the encryption process to secure data storage. The proposed method is finally simulated using various simulation settings to demonstrate its effectiveness, and the outcomes are contrasted with those of cutting-edge approaches. The findings indicate that the suggested plan is more efficient than the current one regarding resource use, power usage, responsiveness, etc. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recently, the development of Low Earth Orbit (LEO) satellites and the advancement of the Mobile Edge Computing (MEC) paradigm have driven the emergence of the Satellite Mobile Edge Computing (Sat-MEC). Sat-MEC has been developed to support communication and task computation for Internet of Things (IoT) Mobile Devices (IMDs) in the absence of terrestrial networks. However, due to the heterogeneity of tasks and Sat-MEC servers, it is still a great challenge to efficiently schedule tasks in Sat-MEC servers. Here, we propose a scheduling algorithm based on the Deep Reinforcement Learning (DRL) method in the Sat-MEC architecture to minimize the average task processing time. We consider multiple factors, including the cooperation between LEO satellites, the concurrency and heterogeneity of tasks, the dynamics of LEO satellites, the heterogeneity of the computational capacity of Sat-MEC servers, and the heterogeneity of the initial queue for task computation. Further, we use the self-attention mechanism to act as a Q-network to extract high-dimensional dynamic information of tasks and Sat-MEC servers. In this work, we model the Sat-MEC environment simulation at the application level and propose a DRL-based task scheduling algorithm. The simulation results confirm the effectiveness of our proposed scheduling algorithm, which reduces the average task processing time by 22.1 % , 30.6 % , and 41.3 % , compared to the genetic algorithm(GA), the greedy algorithm, and the random algorithm, respectively. [ABSTRACT FROM AUTHOR]

The Internet of Things offers a vast infrastructure where numerous devices interact to collect data or perform processing activities (tasks). These devices are, usually, equipped with sensors, software and storage capabilities being able to process the collected data. Task scheduling in edge computing environments has gained considerable attention lately due to the fact that the Edge computing provides lower latency compared to the Cloud. The main challenge is to find a way to maximize the utilization of limited resources available in the edge compared to the Cloud and minimize response time. Many research efforts have been published in order to overcome this challenge. The main limitation of these efforts is the fact that they do not account for task requirements or task correlation that originates from these requirements. In this paper, we focus on the development of a mechanism that utilizes correlation between tasks and takes task requirements into consideration in order to provide efficient task scheduling. Our vision is to minimize task failures and maximize resource utilization with great benefits for the efficient management of the limited resources. [ABSTRACT FROM AUTHOR]

A multi-strategy particle swarm optimization (MSPSO) algorithm was proposed to overcome the slow convergence, low accuracy, and easy fall into local extrema of the traditional particle swarm optimization algorithm in solving cloud computing task scheduling, which integrated the two optimization objectives of minimum maximum completion time and optimal total task execution time. The algorithm incorporated the simulated annealing algorithm, the hunger games search, and the dual variance restriction strategy. Firstly, the inertia weights were dynamically updated by the simulated annealing algorithm to balance the global search and local search of the particle swarm optimization algorithm and help the particles jump out of the local extremes. Then, the hunger games search algorithm was introduced to optimize the particle position update strategy to speed up the particle convergence in the later stages of the algorithm. Finally, a dual variational restriction strategy was used to restrict both particle velocity and position to avoid particle transgression. Comparing experiments with the other three particle swarm optimization algorithms, MSPSO has better performance in the three aspects of average, minimum, and standard deviation of fitness. Through the simulation, MSPSO shows significant advantages in solving cloud computing task scheduling problems with different task sizes in terms of both total cost and minimization of fitness values. In particular, when the task size is 40, the total cost of MSPSO is 14. 4%, 15. 3%, and 11. 2% lower than other algorithms, and the fitness values are 10. 5%, 10. 6%, and 7. 6% lower, respectively, verifying the effectiveness of the proposed algorithm in solving the cloud computing task scheduling problem. [ABSTRACT FROM AUTHOR]

To serve various tasks requested by various end devices with different requirements, end-edge-cloud (E2C) has attracted more and more attention from specialists in both academia and industry, by combining both benefits of edge and cloud computing. But nowadays, E2C still suffers from low service quality and resource efficiency, due to the geographical distribution of edge resources and the high dynamic of network topology and user mobility. To address these issues, this paper focuses on task offloading, which makes decisions that which resources are allocated to tasks for their processing. This paper first formulates the problem into binary non-linear programming and then proposes a particle swarm optimization (PSO)-based algorithm to solve the problem. The proposed algorithm exploits an imbalance mutation operator and a task rescheduling approach to improve the performance of PSO. The proposed algorithm concerns the resource heterogeneity by correlating the probability that a computing node is decided to process a task with its capacity, by the imbalance mutation. The task rescheduling approach improves the acceptance ratio for a task offloading solution, by reassigning rejected tasks to computing nodes with available resources. Extensive simulated experiments are conducted. And the results show that the proposed offloading algorithm has an 8.93%-37.0% higher acceptance ratio than ten of the classical and up-to-date algorithms, and verify the effectiveness of the imbalanced mutation and the task rescheduling. [ABSTRACT FROM AUTHOR]

Task scheduling poses a wide variety of challenges in the cloud computing paradigm, as heterogeneous tasks from a variety of resources come onto cloud platforms. The most important challenge in this paradigm is to avoid single points of failure, as tasks of various users are running at the cloud provider, and it is very important to improve fault tolerance and maintain negligible downtime in order to render services to a wide range of customers around the world. In this paper, to tackle this challenge, we precisely calculated priorities of tasks for virtual machines (VMs) based on unit electricity cost and these priorities are fed to the scheduler. This scheduler is modeled using a deep reinforcement learning technique which is known as the DQN model to make decisions and generate schedules optimally for VMs based on priorities fed to the scheduler. This research is extensively conducted on Cloudsim. In this research, a real-time dataset known as Google Cloud Jobs is used and is given as input to the algorithm. This research is carried out in two phases by categorizing the dataset as a regular or large dataset with real-time tasks with fixed and varied VMs in both datasets. Our proposed DRFTSA is compared to existing state-of-the-art approaches, i.e., PSO, ACO, and GA algorithms, and results reveal that the proposed DRFTSA minimizes makespan compared to PSO, GA, and ACO by 30.97%, 35.1%, and 37.12%, rates of failure by 39.4%, 44.13%, and 46.19%, and energy consumption by 18.81%, 23.07%, and 28.8%, respectively, for both regular and large datasets for both fixed and varied VMs. [ABSTRACT FROM AUTHOR]

Copyright of Journal on Communication / Tongxin Xuebao is the property of Journal on Communications Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the volume and velocity of Big Data continue to grow, traditional cloud computing approaches struggle to meet the demands of real-time processing and low latency. Fog computing, with its distributed network of edge devices, emerges as a compelling solution. However, efficient task scheduling in fog computing remains a challenge due to its inherently multi-objective nature, balancing factors like execution time, response time, and resource utilization. This paper proposes a hybrid Genetic Algorithm (GA)-Particle Swarm Optimization (PSO) algorithm to optimize multi-objective task scheduling in fog computing environments. The hybrid approach combines the strengths of GA and PSO, achieving effective exploration and exploitation of the search space, leading to improved performance compared to traditional single-algorithm approaches. The proposed hybrid algorithm results improved the execution time by 85.68% when compared with GA algorithm, by 84% when compared with Hybrid PWOA and by 51.03% when compared with PSO algorithm as well as it improved the response time by 67.28% when compared with GA algorithm, by 54.24% when compared with Hybrid PWOA and by 75.40% when compared with PSO algorithm as well as it improved the completion time by 68.69% when compared with GA algorithm, by 98.91% when compared with Hybrid PWOA and by 75.90% when compared with PSO algorithm when various tasks inputs are given. The proposed hybrid algorithm results also improved the execution time by 84.87% when compared with GA algorithm, by 88.64% when compared with Hybrid PWOA and by 85.07% when compared with PSO algorithm it improved the response time by 65.92% when compared with GA algorithm, by 80.51% when compared with Hybrid PWOA and by 85.26% when compared with PSO algorithm as well as it improved the completion time by 67.60% when compared with GA algorithm, by 81.34% when compared with Hybrid PWOA and by 85.23% when compared with PSO algorithm when various fog nodes are given.

As the IoT devices are highly ubiquitous and connected, their computational tasks can be processed on the Multi-access edge computing (MEC) servers because of the IoT devices’ limited battery, computing power and storage capacities. Due to the heterogeneity of IoT devices and MEC devices’ limited capabilities, tasks should be offloaded efficiently to MEC servers mainly and then to the Clouds (fog nodes) if necessary for fulfilling tasks’ computational requirements. The proposed solution presents a task offloading decision using base stations of the network and queued task scheduling. The base station, which is the edge orchestrator, will decide on where to offload (edge servers or cloud) or compute locally. For handling heterogeneous tasks, a maximum tolerable latency is included. It is shown that a 3% to 7% improvement in the number of failed tasks, more than 7.4% in the number of successfully completed tasks, an improvement by more than 0.85 s in the average execution time and more than 7% in network communication, which directly impacts the energy of edge devices. The simulation results show that this work performed better in decreasing the number of failed tasks due to latency, decreasing energy consumption and minimizing the average execution time of tasks.

Healthcare industries have begun using modern technologies and tools like cloud computing these days. When cloud computing and assisted technologies are used in the healthcare domain the storage cost improves along with the quality and time availability. The present work makes use of cryptography based architecture for improving the overall security aspects. However, the tasks of the user take a longer duration for the execution to complete when the needed resources are unavailable on the main server. ICSA (Improved Cuckoo Search Algorithm) with DRL (Deep Reinforcement Learning) to solve this issue. The main goal of this work is to increase overall security and reduce execution times of jobs. The objective also includes using underutilized resources. Scheduling jobs, Binary In-order Traversal Trees with weights are used. Subsequently, DRL algorithm has been used to decrease the space complexity by splitting the individual resources. There will be idle resources in a state space that are used in allocation of tasks. The scheduled tasks will then do a search on the resources based on the ICSA algorithm. The server will then distribute the resources to the action area after an optimal resource has been chosen and assigned to the job. DRL for resource allocation so that the inactive resource usage is minimized and the execution time is reduced. Finally, MTAC-IBEA (multi tenant authentication control with improved blowfish encryption algorithm) for decrypt health data. The outcomes of simulation demonstrate that the suggested method offers optimum work schedules, resource allocations, and security in e-healthcare systems.

Deep neural networks (DNNs) have gained considerable attention for their expressive capabilities, but unfortunately they have serious robustness risks. Formal verification is an important technique to ensure network reliability. However, current verification techniques are unsatisfactory in time performance, which hinders the practical applications. To address this issue, we propose an efficient optimization method based on parallel acceleration with more computing resources. The method involves the speedup configuration of a partition-based verification aligned with the structures and robustness formal specifications of DNNs. A parallel verification framework is designed specifically for neural network verification systems, which integrates various auxiliary modules and accommodates diverse verification modes. The efficient parallel scheduling of verification queries within the framework enhances resource utilization and enables the system to process a substantial volume of verification tasks. We conduct extensive experiments on multiple commonly used verification benchmarks to demonstrate the rationality and effectiveness of the proposed method. The results show that higher efficiency is achieved after parallel optimization integration.

The artificial intelligence (AI) industry is increasingly integrating with diverse sectors such as smart logistics, FinTech, entertainment, and cloud computing. This expansion has led to the coexistence of heterogeneous applications within multi-tenant systems, presenting significant scheduling challenges. This paper addresses these challenges by exploring the scheduling of various machine learning workloads in large-scale, multi-tenant cloud systems that utilize heterogeneous GPUs. Traditional scheduling strategies often struggle to achieve satisfactory results due to low GPU utilization in these complex environments. To address this issue, we propose a novel scheduling approach that employs a genetic optimization technique, implemented within a process-oriented discrete-event simulation framework, to effectively orchestrate various machine learning tasks. We evaluate our approach using workload traces from Alibaba’s MLaaS cluster with over 6000 heterogeneous GPUs. The results show that our scheduling improves GPU utilization by 12.8% compared to Round-Robin scheduling, demonstrating the effectiveness of the solution in optimizing cloud-based GPU scheduling.