Task Execution Time Research Articles

Load-aware task migration algorithm toward adaptive load balancing in Edge Computing

The rapid advancement of the Internet of Things (IoT) is leading to more and more devices joining the network to interact with information, which requires improving the performance of IoT applications to accommodate more data, faster response times, and more complex tasks. Edge computing, as a new computing paradigm, brings resource contention and load imbalance while reducing communication overhead and task latency. This paper addresses the workload distribution challenge in edge networks, aiming to optimize resource utilization and thereby enhance IoT application performance. To achieve this goal, we present the Load-aware Task Migration (LATM) algorithm. Firstly, we present a load state detection model that captures edge nodes’ workloads and dynamically classifies them according to their resource requirements. We then propose an innovative optimization problem, transforming task migration into a weighted tripartite graph matching problem. This problem leverages the Kuhn–Munkres(KM) task migration algorithm to attain the optimal matching between tasks and nodes. Finally, we assess the algorithm’s performance through experimental simulation. The experimental results underscore the algorithm’s substantial potential in reducing task response times, task execution times, load balance, and enhancing resource utilization.

Model and metaheuristic for human–robot collaboration assembly line worker assignment and balancing problem

Given the Industry 5.0 trend towards human-centric and resilient industries, workers continue to be considered as a valuable and irreplaceable resource. Human–robot collaboration (HRC) is a promising production mode that combines the advantages of both human workers and robots, resulting in improved productivity and reduced ergonomic risks for workers. In this study, we present one of the first attempts to address the human–robot collaboration assembly line worker assignment and balancing problem (HRCALWABP), which allows workers and robots to perform tasks in parallel or in collaboration. Workers are heterogeneous, leading to variations in task execution times. We formulate a mixed-integer linear programming (MILP) model that minimizes the cycle time and propose a tight lower/upper bound. A rebalancing process is further considered in this study. Due to the complexity of HRCALWABP, we develop an improved adaptive neighborhood simulated annealing algorithm (IASA). An adaptive mechanism is applied to the IASA to dynamically adjust the selection probability of the designed neighborhood structures and operators, and a restart mechanism is developed for improving the search capacity. Extensive computational experiments are conducted to evaluate the performance of both the MILP and IASA, and the results confirm the superiority of the IASA compared to the MILP and other existing algorithms.

Meta Reinforcement Learning for Multi-Task Offloading in Vehicular Edge Computing

Mobile edge computing has been a promising solution to enable real-time service in vehicular networks. However, due to high dynamics of mobile environment and heterogeneous features of vehicular services, traditional expert-based or learning-based strategies has to update handcrafted parameters or retrain learning model, which leads to intolerant overhead. Therefore, this paper investigates the problem of multi-task offloading (MTO), where there exist multiple offloading scenarios with varying parameters, such as task topology, resource requirement and transmission/computation capability. The objective is to design a unified solution to minimize task execution time under different MTO scenarios. Accordingly, we develop a Seq2seq-based Meta Reinforcement Learning algorithm for MTO (SMRL-MTO). Specifically, a bidirectional gated recurrent units integrated with attention mechanism is designed to determine offloading action by encoding sequential offloading actions and showing different preferences to different parts of input sequence. Particularly, a meta reinforcement learning framework is designed based on model-agnostic meta learning, which trains a meta policy offline and fast adapts to new MTO scenario within a few training steps. Finally, we conduct performance evaluation based on task generator DAGGEN and realistic vehicular traces, which shows that the SMRL-MTO reduces task execution time by 11.36% on average compared with greedy algorithm.

A Secure and Decentralized DLaaS Platform for Edge Resource Scheduling Against Adversarial Attacks

Edge Computing is promising for latency-sensitive applications. However, current edge resource scheduling is inefficient. Deep Learning as a Service (DLaaS) provides deep learning methods to optimize the resource scheduling problem, but faces great challenges of security and reliability. On one hand, DLaaS training agents and raw data are exposed to various adversarial attacks. On the other hand, dishonest DLaaS trainers can generate poisoned models to attack the DLaaS system. In this paper, we propose SAPE, a Secure and decentralized DLAaS Platform in Edge computing. SAPE allows users to submit their tasks, which will be scheduled to the appropriate edge clusters to minimize the task execution time. We formulate the resource scheduling problem and develop the federated deep reinforcement learning (DRL) method to optimize the problem and resist the adversarial attacks of DLaaS. We utilize blockchain and propose a consortium-based verification scheme to improve the reliability of the federated training process, protecting the DLaaS models from being poisoned and compromised. We conduct experiments to evaluate the latency and security performance of SAPE and the federated DRL scheduling policy. The results show that SAPE outperforms the traditional schemes when defending against adversarial attacks towards the DLaaS platform in edge computing.

Stochastic models for time complexity of computing tasks: I. Development principles, statistical data mining, identification problems

The paper contains the first part of an investigation devoted to the design of the mathematical models for the execution time of user tasks carried out on the virtual calculating nodes. We suppose that the execution time is a random value with the mean and variance depending on the node resources, task parameters, and the current characteristics of the node state. We discover the key features of the mean and variance functions and specify some of their particular cases. Both the mean and variance functions depend on the unknown parameters, and the design of the stochastic model for the time complexity leads to the parameter identification in the form of the generalized maximum likelihood estimates under the heterogeneous statistical information. The paper also contains recommendations concerning the gathering and subsequent usage of this information: the node testbed preparation, stress test planning, and the obtained data processing. The specific illustrating examples of the proposed mathematical model will be presented in the subsequent parts of the investigation.

Speed of performing complex movement tasks under decision-making conditions as a determinant of the tactical preparation level in kickboxers

This study aimed to evaluate the relationship between the speed of performing a complex motor task carried out under conditions requiring decision-making and the sports level of the kickboxers being studied. The authors constructed a test involving a complex author’s kickboxing task that mirrored the competitive conditions during a sports fight. Forty-seven K-1 kickboxing Polish National Team members (37 men and 10 women) performed a specific series of strikes across three variants. The relationship between the speed of these complex movement tasks, performed under decision-making conditions, and the sports level of the kickboxers, was evaluated. Deciding to start or change an action in reaction to external stimuli significantly (p < 0.001) increased the total task completion time in the male and female subject groups. The time spent deciding to take action and the time spent on deciding on the action were not significantly different. Quick execution of complex tasks under decision-making conditions, such as selecting the appropriate technical and tactical action, can become a decisive factor in determining a sports result. Making decisions to start or change an action as a reaction to external stimuli significantly (p < 0.001) extended the total time of task execution in the studied group. However, the time spent deciding to start the action and the time devoted to deciding during the action did not differ significantly. Therefore, the tactical solution an athlete uses makes no difference, though they must perform it confidently and with minimal time loss.

Resource allocation on periotity based schuduling and improve the security using DSSHA-256

Cloud computing has gained popularity with advancements in virtualization technology and the deployment of 5G. However, scheduling workload in a heterogeneous multi-cloud environment is a complicated process. Users of cloud services want to ensure that their data is secure and private, especially sensitive or proprietary information. Several research works have been proposed to solve the challenges associated with cloud computing. The proposed Adaptive Priority based scheduling (PBS) focuses on reducing data access completion time and computation expense for task scheduling in cloud computing. PBS assigns tasks depending on its size and selects the minimum cost path for data access. It contains a task register, scheduler, and task execution components for efficient task execution. The proposed system also executes a double signature mechanism for data privacy and security in data storage. This study correlates the performance of three algorithms, PBS, (Task Requirement Degree) TRD and (recommended a Risk adaptive Access Control) RADAC, in terms of task execution time and makespan time. The experimental results demonstrate that PBS outperforms TRD and RADAC in both metrics, as the number of tasks increases. PBS has a minimum task execution time and a lower makespan time than the other two algorithms

Optimized task offloading strategy in IoT edge computing network

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.

Telemetry-aided cooperative multi-agent online reinforcement learning for DAG task scheduling in computing power networks

As demand for computing power and low latency in intelligence applications grows, the efficient management and coordination of resources in computing power networks become crucial. This paper presents a telemetry-aided multi-agent cooperation framework for DAG task scheduling in computing power networks. Utilizing distributed agents with network telemetry, the framework accurately assesses local network state information, formulates scheduling policies, and assigns tasks to edge servers. An online learning algorithm for DAG task scheduling is also introduced to enhance the cooperation strategy in decision-making, enabling rapid task scheduling and resource allocation decisions. Simulation results demonstrate a minimum 13.5% reduction in total task execution time compared to sub-optimal methods, along with improved node and link load balancing.

Human beings influencing assembly line performance: a comparison of job rotation strategies

Industries recently have faced high uncertain market demand with a greater product variety and a shorter life cycle. The primary aim of assembly systems is to increase line efficiency by maximizing the ratio of throughput to incurred costs while maintaining high flexibility. Workers are essential in determining line performance since most assembly tasks are still manual. Consequently, worker diversity plays a critical role in the operation of an assembly line, not only in terms of efficiency and productivity, but also from a human perspective. The human factor has a significant impact on task execution times and the overall production process; in any event, few studies considered human beings in assembly line operations. This study aims to explore the effect of human beings on assembly line performance; the case of an Italian company in which workers’ behavior deeply influences production performance is presented, with the aim of analyzing different alternatives for the planning strategy in order to meet this requirement. The studied assembly line consists of three manual workstations and two automated workstations. It operates in a multi-model production environment and has an imbalance level of 50%. The proposal is to manage the allocation of workers through job rotation scheduling to ensure equal treatment despite different levels of efficiency. The study outlines three scheduling alternatives, highlighting the advantages and disadvantages of each.

Multicriteria generalized regressive neural federated learning for cloud computing task scheduling and resource allocation

Cloud computing has arisen as a shrewd and well known worldview for people and associations to work with the entrance and use of registering assets through the web.With the rapid growth of cloud computing technology, efficiently running big data applications within minimal time has become a significant challenge. In this dynamic and scalable environment, effective resource allocation and task scheduling of big data applications play pivotal roles in optimizing performance, enhancing efficiency, and ensuring cost-effectiveness. In environments involving remote computing, task scheduling is a crucial consideration. In order to effectively accomplish resource-optimal task scheduling and minimize overall task execution time, a novel technique called Multicriteria Generalized Regressive Neural Federated Learning (MGRNFL) is developed to address the particular issues in cloud systems. Tasks from several users arrive at the cloud server at the start of the procedure. The cloud server's job scheduler then uses Multicriteria Federated Learning to carry out resource-optimal task scheduling. A decentralized machine learning technique called federated learning (FL) enables model training across several tasks that are gathered from cloud computing customers. This decentralized approach primarily focuses on learning from datasets to obtain a global model by aggregating the results of local models. The proposed techniques involve two different steps: local training models and global aggregation models. In the local training model, the task scheduler determines the resource-optimal virtual machine in the cloud server using a Generalized Regression Neural Network (GRNN) based on multicriteria functions of the virtual machine, such as energy, memory, CPU, and bandwidth. Based on these objective functions, resource-efficient virtual machines are determined to schedule multiple user tasks. The locally updated models are then combined and fed into the global aggregation model. Calculated within the global aggregation model is the weighted total of locally updated findings. The algorithm iterates through this process till the maximum number of times. In order to schedule incoming tasks, the resource-optimal virtual machine is found. Various quantitative criteria are used for the experimental evaluation, including makespan, throughput in relation to the number of tasks, and task scheduling efficiency.

System-Level Energy-Aware Design Methodology Towards End-To-End Response Time Optimization

Energy provision is known and limited for battery-constrained/powered systems (e.g., mobile phones, electric cars, robots, and wireless sensor networks). System-level energy-aware design methodologies have been proposed to control energy usage for energy provision guarantee, and to optimize the end-to-end response time for high-performance in heterogeneous energy-aware systems, where energy pre-assignment strategies are considered as their main contributions. However, when pre-assigning energy to tasks, these strategies either are overly pessimistic or adopt an average manner without a customizable approach to specific tasks. In this paper, we propose an effective algorithm called ratio-based energy pre-assignment (REP) to be customizable to split the available energy according to the energy ratios of individual tasks. Experiments confirm that REP outperforms the state-of-the-art three algorithms of the same type. After REP is used, we further propose a new innovation algorithm called energy surplus reduction (ESR) to reduce the execution time of small partial tasks, thereby optimizing the end-to-end response time within its energy provision. Experiments confirm ESR can reduce the energy usages of small partial tasks to achieve sufficient response time optimization.

Mechatronics system for solving SuDoKu puzzle based on Cartesian robot

The article describes an original solution of a mechatronic device with a Cartesian robot and a character recognition system for autonomous solving the SuDoKu puzzle. The device demonstrates the use of intelligent mechatronic devices for tasks that are difficult to algorithmize. The work contains a description of the mechanical executive system, including the motor apparatus of the system, a description of the electrical and information subsystem, and the software responsible for controlling the device in question. The OCR system operation principle, responsible for recognizing and locating characters on the SuDoKu board, is explained in the article. It also presents how to find a solution using the Backtracking algorithm. The results of testing the correct operation of the designed mechatronic system and estimating the execution time of individual test tasks are presented here.

Blind people can actively manipulate virtual objects with a novel tactile device

Frequently in rehabilitation, visually impaired persons are passive agents of exercises with fixed environmental constraints. In fact, a printed tactile map, i.e. a particular picture with a specific spatial arrangement, can usually not be edited. Interaction with map content, instead, facilitates the learning of spatial skills because it exploits mental imagery, manipulation and strategic planning simultaneously. However, it has rarely been applied to maps, mainly because of technological limitations. This study aims to understand if visually impaired people can autonomously build objects that are completely virtual. Specifically, we investigated if a group of twelve blind persons, with a wide age range, could exploit mental imagery to interact with virtual content and actively manipulate it by means of a haptic device. The device is mouse-shaped and designed to jointly perceive, with one finger only, local tactile height and inclination cues of arbitrary scalar fields. Spatial information can be mentally constructed by integrating local tactile cues, given by the device, with global proprioceptive cues, given by hand and arm motion. The experiment consisted of a bi-manual task, in which one hand explored some basic virtual objects and the other hand acted on a keyboard to change the position of one object in real-time. The goal was to merge basic objects into more complex objects, like a puzzle. The experiment spanned different resolutions of the tactile information. We measured task accuracy, efficiency, usability and execution time. The average accuracy in solving the puzzle was 90.5%. Importantly, accuracy was linearly predicted by efficiency, measured as the number of moves needed to solve the task. Subjective parameters linked to usability and spatial resolutions did not predict accuracy; gender modulated the execution time, with men being faster than women. Overall, we show that building purely virtual tactile objects is possible in absence of vision and that the process is measurable and achievable in partial autonomy. Introducing virtual tactile graphics in rehabilitation protocols could facilitate the stimulation of mental imagery, a basic element for the ability to orient in space. The behavioural variable introduced in the current study can be calculated after each trial and therefore could be used to automatically measure and tailor protocols to specific user needs. In perspective, our experimental setup can inspire remote rehabilitation scenarios for visually impaired people.

Modelling the Reliability of Logistics Flows in a Complex Production System

This paper analyses the disruptions occurring in a production system determining the operating states of a single machine. A system with a convergent production character, in which both single flows (streams) and multi-stream flows occur, was considered. In this paper, a two-level formalisation of the production system (PS) was made according to complex systems theory. The continuity analysis was performed at the operational level (manufacturing machine level). The definition of the kth survival value and the quasi-coherence property defined on chains of synchronous relations were used to determine the impact of interruption of the processed material flow on uninterrupted machine operation. The developed methodology is presented in terms of shaping the energy efficiency of technical objects with the highest power demand (the furnace of an automatic paint shop and the furnace of a glass tempering line were taken into consideration). The proposed methodology is used to optimise energy consumption in complex production structures. The model presented is utilitarian in nature—it can be applied to any technical system where there is randomness of task execution times and randomness of unplanned events. This paper considers the case in which two mutually independent random variables determining the duration of correct operation TP and the duration of breakdown TB are determined by a given distribution: Gaussian and Gamma family distributions (including combinations of exponential and Erlang distributions). A formalised methodology is also developed to determine the stability of system operation, as well as to assess the potential risk for arbitrary system evaluation parameters.

A Learning Game-Based Approach to Task-Dependent Edge Resource Allocation

The existing research on dependent task offloading and resource allocation assumes that edge servers can provide computational and communication resources free of charge. This paper proposes a two-stage resource allocation method to address this issue. In the first stage, users incentivize edge servers to provide resources. We formulate the incentive problem in this stage as a multivariate Stackelberg game, which takes into account both computational and communication resources. In addition, we also analyze the uniqueness of the Stackelberg equilibrium under information sharing conditions. Considering the privacy issues of the participants, the research is extended to scenarios without information sharing, where the multivariable game problem is modeled as a partially observable Markov decision process (POMDP). In order to obtain the optimal incentive decision in this scenario, a reinforcement learning algorithm based on the learning game is designed. In the second stage, we propose a greedy-based deep reinforcement learning algorithm that is aimed at minimizing task execution time by optimizing resource and task allocation strategies. Finally, the simulation results demonstrate that the algorithm designed for non-information sharing scenarios can effectively approximate the theoretical Stackelberg equilibrium, and its performance is found to be better than that of the other three benchmark methods. After the allocation of resources and sub-tasks by the greedy-based deep reinforcement learning algorithm, the execution delay of the dependent task is significantly lower than that in local processing.

INFLUENCE OF NETWORK STRUCTURE AND AGENT PROPERTY ON SYSTEM PERFORMANCE

System structure can affect or decide the system function. Many pioneers have analyzed the impact of system’s macro-statistical characteristics, such as degree distribution and giant component, on system performance. But only few research works were conducted on the relation of mesoscopic structure and agent property with system task performance. In this paper, we designed a scenario that, in a multiagent system, agents will try their best to form a qualified team to fulfill more system tasks under the requirements from agent property, structure and task. The theoretical and simulation results show that the agent link network, agent properties and task requirement will co-affect the dynamic team formation and at last have serious effects on a system’s task completion ratio and performance. Some factors such as network density and task introduction period have positive influence. Task execution time and team size have negative influence. Some factors show a counter-intuitive influence. The clustering coefficient has not much influence as people expected and the task publicity time isn’t bigger the better. Notably, system performance is affected by the coupling effect, instead of the independent effects of all factors. The effect of system structure on system function conditionally relies on the support from agent ability and task requirement.

A parallel computing framework for large-scale microscopic traffic simulation based on spectral partitioning

This paper introduces a parallel computing framework based on the Spectral Partitioning (SP) method designed to enhance the computational efficiency of large-scale microscopic traffic simulation (LSMTS). The framework employs the SP method to partition road networks, taking into account vehicle information and road information as constitutive components for node weight determination. Micro-simulation relies on vehicle information from both preceding and following vehicles to accurately infer the operational states of a vehicle. However, network partitioning can disrupt the flow of vehicle information, resulting in its loss. To address this, the proposed framework incorporates a boundary transmission method to ensure simulation accuracy and precision. This study presents an improved SP (iSP) method tailored for LSMTS, further enhancing the partitioning results achieved through the SP method. Lastly, the framework's validity is confirmed through road network experiments of varying scales and densities, with comparisons made to existing parallel simulation methods. The results demonstrate that the framework significantly reduces the execution time of simulation tasks while maintaining a high level of load balance and minimizing communication overhead.

Collaborative computation offloading for scheduling emergency tasks in SDN-based mobile edge computing networks

Due to the growing demand for time-intensive tasks, several tasks coexist, some of which last for a long time or only occur once in a while, such as emergencies. Emergencies such as natural disasters, accidents or medical emergencies require immediate attention and often demand real-time execution. Such tasks are the most difficult to plan for and foresee. Planning, resource allocation, and clear communication between all involved parties and network layers are crucial for scheduling emergency tasks. In the extensive literature, when an emergency task triggers, it will be handled like any other regular task. If the deadline is missed, a catastrophe will ensue. They ignored the impact of insufficient mobile edge computing (MEC) capacity and network congestion, which might result in execution delays. Collaborative offloading, which involves distributing computation tasks across multiple servers, shows promise in enhancing MEC network performance, particularly in emergency scenarios. In this context, efficient task scheduling plays a vital role in minimizing the total execution time of regular tasks while meeting the deadlines of emergency tasks. Our proposed scheme utilizes a collaborative offloading approach to schedule emergency tasks in MEC networks, leveraging the computing capacity of edge-deployed MEC servers. By utilizing the software-defined networking (SDN)’s global view of the network, task requests are collected and allocated to suitable MEC servers capable of meeting the demands. To address key challenges, our scheme propose four scheduling algorithms to address the following issues: (i) ensuring tasks are assigned to the nearest MEC server with sufficient computational resources, (ii) controlling a threshold to prevent network congestion, (iii) selecting an optimal collaborative MEC server for executing overloaded tasks based on collaborative offloading decisions, and (iv) allocating resources for emergency tasks when triggered to meet urgent deadlines by stealing resources from regular tasks without compromising their deadlines. Extensive simulations were conducted to assess the effectiveness of the proposed scheme. The results clearly illustrate its enhanced performance in terms of the total execution time of regular tasks and the ability to meet deadlines for emergency tasks.

Minimum-time and minimum-energy trajectory planning under dynamic constraints for a quadrotor

This article proposes an approach for optimizing the trajectory planning of quadrotors in structured environments, taking into consideration the trade-off between task execution time and energy consumption. The constraints taken into account are geometrical (boundary conditions in position and orientation, obstacle avoidance), kinematic (boundary conditions in velocity, linear velocity, and acceleration limits of the system), and dynamic (limit capacities in torque of the actuators, constraints related to the under-actuation of the system). The approach extends the Random Trajectory Profile Approach (RPA) to the case of quadrotors. The results of this approach are validated through experimental tests and compared with those in the literature, demonstrating its effectiveness in offline and online scenarios. The proposed approach offers a promising solution for achieving optimal trajectory planning of quadrotors in structured environments.