Execution Latency Research Articles

Joint edge caching and computation offloading for heterogeneous tasks in MEC-enabled vehicular networks

Edge caching is an effective paradigm that can significantly reduce the computation task offloading latency for mobile edge computing (MEC) in vehicular networks, while also alleviating the backhaul transmission pressure for retrieving content data from the cloud server. However, most existing works fail to address how to handle heterogeneous tasks generated by vehicle terminals (VTs), especially in complex scenarios where both computation and content tasks are generated simultaneously. In this paper, we consider a mobility-aware vehicular network model where VTs simultaneously generate heterogeneous task requests, i.e., a computation task and a content task, and investigate joint optimization of caching for heterogeneous tasks data, computation offloading, and computing resource allocation. In order to optimize the latency for processing the heterogeneous tasks, an average execution latency minimization problem with sojourn time and caching capacity constraints is formulated. We decompose this problem into two tractable subproblems, i.e., caching optimization subproblem, and computation offloading and resource allocation optimization subproblem. We first develop a dynamic programming (DP) algorithm to obtain the optimal caching strategies for heterogeneous tasks data. We compare the obtained content retrieval latency with the local computing latency, and derive the optimal computation offloading and edge computing resource allocation solutions. On this basis, we propose a joint computation offloading and resource allocation (JCORA) algorithm to determine the computing resources allocated to each VT and corresponding computation offloading strategy. Numerical results indicate that the proposed algorithm, which integrates DP algorithm and JCORA algorithm, can achieve lower execution latency for heterogeneous tasks compared to the benchmark schemes. Additionally, for task loss scenarios where the sojourn time constraint cannot be met, the impact of VT mobility on the task loss probability is also revealed.

A Review of Algorithms and Platforms for Offloading Decisions in Mobile Cloud Computing

With the substantial growth of mobile applications and the emergence of cloud computing concepts, therefore mobile Cloud Computing (MCC) has been introduced as a potential mobile service technology. Mobile has limited resources, battery life, network bandwidth, storage, and processor, avoid mobile limitations by sending heavy computation to the cloud to get better performance in a short time, the operation of sending data, and get the result of computation call offloading. In this paper, a survey about offloading types is discussed that takes care of many issues such as offloading algorithms, platforms, metrics (that are used with this algorithm and its equations), mobile cloud architecture, and the advantages of using the mobile cloud. The trade-off between local execution of tasks on end-devices and remote execution on the cloud server for minimizing delay time and energy saving. In the form of a multi-objective optimization problem with a focus on reducing overall system power consumption and task execution latency, meta-heuristic algorithms are required to solve this problem which is considered as NP-hardness when the number of tasks is high. To get minimum cost (time and energy) apply partial offloading on specific jobs containing a number of tasks represented in sequences of zeros and ones for example (100111010), when each bit represents a task. The zeros mean the task will be executed in the cloud and the ones mean the task will be executed locally. The decision of processing tasks locally or remotely is important to balance resource utilization. The calculation of task completion time and energy consumption for each task determines which task from the whole job will be executed remotely (been offloaded) and which task will be executed locally. Calculate the total cost (time and energy) for the whole job and determine the minimum total cost. An optimization method based on metaheuristic methods is required to find the best solution. The genetic algorithm is suggested as a metaheuristic Algorithm for future work.

Multi-Stream Scheduling of Inference Pipelines on Edge Devices - a DRL Approach

Low-power edge devices equipped with Graphics Processing Units (GPUs) are a popular target platform for real-time scheduling of inference pipelines. Such application-architecture combinations are popular in Advanced Driver-assistance Systems for aiding in the real-time decision-making of automotive controllers. However, the real-time throughput sustainable by such inference pipelines is limited by resource constraints of the target edge devices. Modern GPUs, both in edge devices and workstation variants, support the facility of concurrent execution of computation kernels and data transfers using the primitive of streams , also allowing for the assignment of priority to these streams. This opens up the possibility of executing computation layers of inference pipelines within a multi-priority, multi-stream environment on the GPU. However, manually co-scheduling such applications while satisfying their throughput requirement and platform memory budget may require an unmanageable number of profiling runs. In this work, we propose a Deep Reinforcement Learning (DRL)-based method for deciding the start time of various operations in each pipeline layer while optimizing the latency of execution of inference pipelines as well as memory consumption. Experimental results demonstrate the promising efficacy of the proposed DRL approach in comparison with the baseline methods, particularly in terms of real-time performance enhancements, schedulability ratio, and memory savings. We have additionally assessed the effectiveness of the proposed DRL approach using a real-time traffic simulation tool IPG CarMaker.

Optimasi dan Modifikasi Debian untuk Meningkatkan Kinerja Sistem Operasi Real-Time

In today's digital era, operating systems play a crucial role in various technological devices. This paper discusses the optimization and modification of Debian, one of the most stable Linux distributions, to enhance its performance as a real-time operating system (RTOS). The primary objectives of this research are to improve the responsiveness, reliability, and stability of Debian in handling real-time tasks. The study involves modifying the kernel, adjusting scheduling settings, optimizing memory management, and integrating specific real-time software. The results of the tests show that the modified Debian provides lower and more stable task execution latency compared to the standard Debian. Tests were conducted using the cyclictest software to measure system latency and Htop to monitor CPU and memory performance. Additionally, the use of the VLC application as a real-world workload demonstrated that the optimized operating system could handle task priorities more efficiently, allocate resources as needed for real-time demands, and maintain stability under heavy workloads. This research significantly contributes to the development of Debian-based RTOS, which can be applied in fields such as industrial automation, robotics, and IoT devices. The optimizations ensure that the operating system can meet the high-performance and real-time reliability demands of these critical applications.

SSO-CCNN: A Correlation-Based Optimized Deep CNN for Brain Tumor Classification Using Sampled PGGAN

Recently, new advancements in technologies have promoted the classification of brain tumors at the early stages to reduce mortality and disease severity. Hence, there is a need for an automatic classification model to automatically segment and classify the tumor regions, which supports researchers and medical practitioners without the need for any expert knowledge. Thus, this research proposes a novel framework called the scatter sharp optimization-based correlation-driven deep CNN model (SSO-CCNN) for classifying brain tumors. The implication of this research is based on the growth of the optimized correlation-enabled deep model, which classifies the tumors using the optimized segments acquired through the developed sampled progressively growing generative adversarial networks (sampled PGGANs). The hyperparameter training is initiated through the designed SSO optimization that is developed by combining the features of the global and local searching phase of flower pollination optimization as well as the adaptive automatic solution convergence of sunflower optimization for precise consequences. The recorded accuracy, sensitivity, and specificity of the SSO-CCNN classification scheme are 97.41%, 97.89%, and 96.93%, respectively, using the brain tumor dataset. In addition, the execution latency was found to be 1.6 s. Thus, the proposed framework can be beneficial to medical experts in tracking and assessing symptoms of brain tumors reliably.

Task execution latency minimization for energy-sensitive IoTs in wireless powered mobile edge computing: A DRL-based method

Wireless powered mobile edge computing (MEC) has become a vital component of future 6G networks, offering efficient computational capabilities to internet of things (IoT) devices and ensuring a stable energy supply. In this paper, we propose an innovative design for a wireless powered MEC-assisted energy-sensitive IoT systems. The system integrates wireless power technology (WPT), allowing IoT devices to efficiently perform tasks under wireless power supply without consuming their battery energy. Therefore, we formulate a dynamic computational task execution latency minimization (DCTELM) problem to tackle the impacts of unpredictable energy requirements and potential communication latency on resource allocation. We also analyze the differences between time division multiple access and non-orthogonal multiple access communication protocols. Given the complexity and dynamic nature of this problem, we define it as a mixed integer nonlinear programming problem. To address this problem, we introduced an enhanced deep reinforcement learning (DRL) algorithm. First, the DCTELM problem is transformed into a Markov decision process (MDP), which simplifies the structure of the problem. Then, after determining the offloading decision, we reveal the convex relationship between resource allocation and task latency. Furthermore, the action space of MDP is further reduced, and a multi-head proximal policy optimization (PPO) algorithm is proposed to deal with the simplified MDP problem. This process reduces the complexity of problem solving, decreases the consumption of computational resources. Simulation results demonstrate that our method outperforms other baselines in terms of computation latency, particularly with the introduction of an exploration strategy during the training phase, which significantly reduces task latency.

Multi-strategy improved sand cat optimization algorithm-based workflow scheduling mechanism for heterogeneous edge computing environment

Edge computing is one of the predominant technologies which facilitates the option of bringing out the computing resources closer to the location of the end users when they are utilized by them. This facility offered by edge computing technology need to reduce the utilization of network bandwidth and response time with respect to the user’s workflow. In this paper, Multi-Strategy Improved Sand Cat Swarm Optimisation Algorithm (MSISCSOA)-based workflow scheduling mechanism is proposed for handling the challenges of workflow scheduling in cloud-edge computing environment. The core objective of this MSISCSOA-based workflow scheduling algorithm targets on minimizing the execution latency and energy consumption to facilitate timely and on-demand end users’ satisfaction of resources. This MSISCSOA scheme is adopted with the improvement introduced using random variation and elite collaborative strategies, such that well-balanced the trade-off between exploration and exploitation is achieved. This improvement is introduced over Sand Cat Optimization Algorithm (SCOA) using the merits of dynamic random search and joint opposite selection strategies that accelerates the convergence of the algorithm with increased global optimization and searching efficiency. It specifically improved SCOA using random variation for escaping from the local point of optimality. It also used well distributed pareto fronts and population evolution multi-strategy that aids in searching solutions with maximized diversity. The simulation experiments conducted using the datasets of Montage, Cybershake, LIGO and SIPHT an average confirmed minimized execution latency of 21.38 % and energy consumptions of 19.56 %, better than the baseline Ant Colony Optimization Algorithm-Based Workflow Scheduling (IACOAWS), Quadratic Penalty Function-based Particle Swarm Optimization Algorithm (QPF-PSOA), Biogeography Optimization (BBO) Algorithm based Multi-Objective Task Scheduling (BBOAMOTS) and Different Evolution-based Task Clustering and Scheduling (DETCS) approaches used for comparative investigation.

Fuzzy logic‐based computation offloading technique in fog computing

AbstractThe fog computing environment expands the capabilities of cloud computing by moving computing, storage, and networking services closer to IoT devices. These resource‐constrained IoT devices often face challenges like high task failure rates and extended execution latency due to data traffic congestion. Distributing IoT services through task offloading across different layers of computing paradigms enhances QoS (Quality of Service) parameters. This endeavor aims to allocate custom workflow‐based real‐time tasks or jobs for processing across various cloud/fog/edge layers, optimizing QoS factors like makespan, energy consumption, and cost. In the fog computing environment, challenges arise due to uncertainties related to job execution locations and the ability to predict future user requirements. Fuzzy logic offers low‐complexity solutions for handling unpredictable and rapidly changing conditions. This paper proposes a hybrid fog‐cloud‐based computing architecture and an intelligent fuzzy logic‐based computation offloading approach. This approach effectively allocates workloads among edge, fog, and cloud layers, resulting in improvements in makespan time (7.51%), energy consumption (4.63%), and cost (13.60%). The proposed method selects suitable processing units or compute nodes for job execution, utilizing heterogeneous resources. Simulation results demonstrate that the proposed methodology outperforms current state‐of‐the‐art algorithms.

Distributed Computation Offloading and Power Control for UAV-Enabled Internet of Medical Things

The advancement of the Internet of Medical Things (IoMT) has led to the emergence of various health and emotion care services, e.g., health monitoring. To cater to increasing computational requirements of IoMT services, Mobile Edge Computing (MEC) has emerged as an indispensable technology in smart health. Benefiting from the cost-effectiveness of deployment, unmanned aerial vehicles (UAVs) equipped with MEC servers in Non-Orthogonal Multiple Access (NOMA) have emerged as a promising solution for providing smart health services in proximity to medical devices (MDs). However, the escalating number of MDs and the limited availability of communication resources of UAVs give rise to a significant increase in transmission latency. Moreover, due to the limited communication range of UAVs, the geographically-distributed MDs lead to workload imbalance of UAVs, which deteriorates the service response delay. To this end, this paper proposes a UAV-enabled Distributed computation Offloading and Power control method with Multi-Agent, named DOPMA, for NOMA-based IoMT environment. Specifically, this paper introduces computation and transmission queue models to analyze the dynamic characteristics of task execution latency and energy consumption. Moreover, a credit assignment scheme-based reward function is designed considering both system-level rewards and rewards tailored to each MD, and an improved multi-agent deep deterministic policy gradient algorithm is developed to derive offloading and power control decisions independently. Extensive simulations demonstrate that the proposed method outperforms existing schemes, achieving \(7.1\% \) reduction in energy consumption and \(16\% \) decrease in average delay.

Enhancing Embedded Object Tracking: A Hardware Acceleration Approach for Real-Time Predictability.

While Siamese object tracking has witnessed significant advancements, its hard real-time behaviour on embedded devices remains inadequately addressed. In many application cases, an embedded implementation should not only have a minimal execution latency, but this latency should ideally also have zero variance, i.e., be predictable. This study aims to address this issue by meticulously analysing real-time predictability across different components of a deep-learning-based video object tracking system. Our detailed experiments not only indicate the superiority of Field-Programmable Gate Array (FPGA) implementations in terms of hard real-time behaviour but also unveil important time predictability bottlenecks. We introduce dedicated hardware accelerators for key processes, focusing on depth-wise cross-correlation and padding operations, utilizing high-level synthesis (HLS). Implemented on a KV260 board, our enhanced tracker exhibits not only a speed up, with a factor of 6.6, in mean execution time but also significant improvements in hard real-time predictability by yielding 11 times less latency variation as compared to our baseline. A subsequent analysis of power consumption reveals our approach's contribution to enhanced power efficiency. These advancements underscore the crucial role of hardware acceleration in realizing time-predictable object tracking on embedded systems, setting new standards for future hardware-software co-design endeavours in this domain.

ConvKyber: Unleashing the Power of AI Accelerators for Faster Kyber with Novel Iteration-based Approaches

The remarkable performance capabilities of AI accelerators offer promising opportunities for accelerating cryptographic algorithms, particularly in the context of lattice-based cryptography. However, current approaches to leveraging AI accelerators often remain at a rudimentary level of implementation, overlooking the intricate internal mechanisms of these devices. Consequently, a significant number of computational resources is underutilized.In this paper, we present a comprehensive exploration of NVIDIA Tensor Cores and introduce a novel framework tailored specifically for Kyber. Firstly, we propose two innovative approaches that efficiently break down Kyber’s NTT into iterative matrix multiplications, resulting in approximately a 75% reduction in costs compared to the state-of-the-art scanning-based methods. Secondly, by reversing the internal mechanisms, we precisely manipulate the internal resources of Tensor Cores using assembly-level code instead of inefficient standard interfaces, eliminating memory accesses and redundant function calls. Finally, building upon our highly optimized NTT, we provide a complete implementation for all parameter sets of Kyber. Our implementation surpasses the state-of-the-art Tensor Core based work, achieving remarkable speed-ups of 1.93x, 1.65x, 1.22x and 3.55x for polyvec_ntt, KeyGen, Enc and Dec in Kyber-1024, respectively. Even when considering execution latency, our throughput-oriented full Kyber implementation maintains an acceptable execution latency. For instance, the execution latency ranges from 1.02 to 5.68 milliseconds for Kyber-1024 on R3080 when achieving the peak throughput.

Reliability-Constrained Task Scheduling for DAG Applications in Mobile Edge Computing

The development of the internet of things (IoT) and 6G has given rise to numerous computation-intensive and latency-sensitive applications, which can be represented as directed acyclic graphs (DAGs). However, achieving these applications poses a huge challenge for user equipment (UE) that are constrained in computational power and battery capacity. In this paper, considering different requirements in various task scenarios, we aim to optimize the execution latency and energy consumption of the entire mobile edge computing (MEC) system. The system consists of single UE and multiple heterogeneous MEC servers to improve the execution efficiency of a DAG application. In addition, the execution reliability of a DAG application is viewed as a constraint. Based on the strong search capability and Pareto optimality theory of the cuckoo search (CS) algorithm and our previously proposed improved multiobjective cuckoo search (IMOCS) algorithm, we improve the initialization process and the update strategy of the external archive, and propose a reliability-constrained multiobjective cuckoo search (RCMOCS) algorithm. According to the simulation results, our proposed RCMOCS algorithm is able to obtain better Pareto frontiers and achieve satisfactory performance while ensuring execution reliability.

Task offloading exploiting grey wolf optimization in collaborative edge computing

The emergence of mobile edge computing (MEC) has brought cloud services to nearby edge servers facilitating penetration of real-time and resource-consuming applications from smart mobile devices at a high rate. The problem of task offloading from mobile devices to the edge servers has been addressed in the state-of-the-art works by introducing collaboration among the MEC servers. However, their contributions are either limited by minimization of service latency or cost reduction. In this paper, we address the problem by developing a multi-objective optimization framework that jointly optimizes the latency, energy consumption, and resource usage cost. The formulated problem is proven to be an NP-hard one. Thus, we develop an evolutionary meta-heuristic solution for the offloading problem, namely WOLVERINE, based on a Binary Multi-objective Grey Wolf Optimization algorithm that achieves a feasible solution within polynomial time having computational complexity of O(M3)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(M^3)$$\\end{document}, where M is an integer that determines the number of segments in each dimension of the objective space. Our experimental results depict that the developed WOLVERINE system achieves as high as 33.33%, 35%, and 40% performance improvements in terms of execution latency, energy, and resource cost, respectively compared to the state-of-the-art.

Natural Language-Driven Dialogue Systems for Support in Physical Medicine and Rehabilitation

This paper presents a natural language-driven dialogue system designed to support healthcare professionals and students in the field of physical medicine and rehabilitation. The system seamlessly integrates concepts from intelligent information systems, data mining, ontologies, and human-computer interaction, employing at its core a rule-based dialogue mechanism. The system harnesses the power of ontology-based graph knowledge, underscoring its domain-specific efficacy. This article delves into the automated knowledge base formation, utilising Python scripts to translate EBSCO’s dataset of articles on physical medicine and rehabilitation into an OWL ontology. This methodology ensures adaptability to the ever-evolving landscape of medical insights. The system’s approach to natural language processing encompasses text preprocessing, semantic category discernment, andSPARQL query creation, providing 26 predefined categories. As an innovation in performance optimisation, the system integrates a strategy to cache precomputed responses using a PostgreSQL database, which aids in resource conservation and reduction in query execution latency. The system’s user engagement avenues are further detailed, showcasing a Telegram bot and an API, enhancing accessibility and user experience. In essence, this article illuminates an advanced, efficient dialogue system for physical medicine and rehabilitation, synthesising multiple computational paradigms, and standing as a beacon for healthcare practitioners and students alike.

DRL-Based Computation Offloading and Resource Allocation in Green MEC-Enabled Maritime-IoT Networks

The maritime Internet of Things (MIoT), a maritime version of the Internet of Things (IoT), is envisioned as a promising solution that can provide ubiquitous connectivity over land and sea. Due to the rapid development of maritime activities and the maritime economy, there is a growing demand for computing-intensive and latency-sensitive maritime applications requiring various energy consumption, communication, and computation resources, posing a significant challenge to MIoT devices due to their limited computational ability and battery capacity. Mobile Edge Computing (MEC), which can handle computation tasks at the network’s edge more efficiently and with less latency, is emerging as a paradigm for fulfilling the ever-increasing demands of MIoT applications. However, the exponential increase in the number of MIoT devices has increased the system’s energy consumption, resulting in increased greenhouse gas emissions and a negative impact on the environment. As a result, it is vital for MIoT networks to take traditional energy usage minimization into account. The integration of renewable energy-harvesting capabilities into base stations or MIoT devices possesses the potential to reduce grid energy consumption and carbon emissions. However, making an effective decision regarding task offloading and resource allocation is crucial for maximizing the utilization of the system’s potential resources and minimizing carbon emissions. In this paper, we first propose a green MEC-enabled maritime IoT network architecture to flexibly provide computing-intensive and latency-sensitive applications for MIoT users. Based on the architecture, we formulate the joint task offloading and resource allocation problem by optimizing the total system execution efficiency (including the total size of completed tasks, task execution latency, and the system’s carbon emissions) and then propose a deep-deterministic-policy-gradient-based joint optimization strategy to solve the problem, eventually obtaining an effective resolution through continuous action space learning in the changing environment. Finally, simulation results confirm that our proposal can yield good performance in system execution efficiency compared to other benchmarks; that is, it can significantly reduce the system’s carbon emissions and tasks’ delay and improve the total size of completed tasks.

Communication-Computation-Aware User Association in MEC HetNets: A Meta-Analysis

The stochastic geometry-based modeling and analysis of large-scale mobile edge computing (MEC) networks are vital for the effective configuration of MEC networks. In this paper, we develop a meta-analytical framework for MEC-enabled heterogeneous networks with the communication-computation-aware (CCA) user association mechanism. Compared with the communication-based user association mechanisms in most existing works, the CCA user association mechanism can capture the impacts of network computation capability on the association process between the user and MEC access point, at the expense of dealing with the more complex coupling of communication and computing. Given the need for interference characterization, we first derive the essential prerequisite quantities (i.e., per-tier association probability, link distance distribution, interferer process intensity, etc.) to represent the computation-dependent interference model. Further, the moment and the meta distribution of the task success offloading probability are derived, based on which we investigate the task execution latency performance, including the communication latency, local computing latency, and edge computing latency. By theoretical analysis and simulation results, it is demonstrated that the proposed analytical framework can provide accurate fine-grained network information for the MEC-enabled HetNets. Moreover, we elaborate on the impacts of the edge computation capability on the network performance and reveal important tradeoffs of the performance metrics.

ADRLO: Adaptive deep reinforcement learning-based offloading for edge computing

Computation offloading, as an efficient and promising computing paradigm for mobile edge computing (MEC), provides optimal computation allocation between MEC servers and Internet of Things (IoT) devices. However, in modern wireless communications, most of the computational tasks are latency-sensitive, presenting an efficiency challenge for offloading services. Moreover, to make the best use of computation resources, it remains an issue to ensure stable optimal offloading for the allocation of computation resources. In this paper, a novel adaptive deep reinforcement learning-based offloading (ADRLO) framework is developed to achieve a stable optimal computation revenue with low execution latency for MEC offloading. Structurally, we implement a residual connected deep neural network (DNN) to generate a series of offloading strategies and use them to obtain the global system computation rate. Especially, the strategy that achieves the maximum computation rate is then selected as experience to support the DNN training, forming a closed-loop deep reinforcement learning (DRL) mechanism. To further enhance the efficiency and stability of the MEC offloading, an adaptive regulator is presented for the framework parameters including the size of action space and the DNN learning rate. Numerical results show that, compared to existing state-of-the-art approaches, our proposal achieves optimal computation revenue, exhibits better convergence performance, and significantly reduces the execution latency by almost 50%.

Task offloading to edge cloud balancing utility and cost for energy harvesting Internet of Things

Task offloading from many Internet of Things (IoT) devices to a mobile edge computing (MEC) system, consisting of multiple collaborative edge servers (CES), results in reduced task execution delay as well as energy consumption. However, the exploitation of computation resources of CESs incurs additional costs. Existing works in the literature either focused on minimizing execution latency or energy consumption. In this paper, we have developed a task offloading policy that aims at making a trade-off between device utility and execution cost. The utility is defined as a function of task execution latency and energy consumption of energy-harvesting IoT devices. The task offloading problem is formulated as a subset selection problem that makes the desired trade-off. The offloading problem is proven to be NP-hard and thus we develop a meta-heuristic approach, namely SCOPE, inspired by Social Cognitive Optimization (SCO) to obtain the desired polynomial time execution. The results show its potency compared to the state-of-the-art methods in terms of task execution latency, energy consumption, utility per unit cost, and task drop rate.

Repetition costs in sequence chunking.

We examined how flexibly we plan sequences of actions when we switch between multiple action sequences. Mastering a sequential skill is assumed to involve integrating successive actions into groups known as chunks that can be efficiently planned and smoothly executed. Chunking is suggested by gains in planning efficiency for long compared to short action sequences following practice and learning associations between actions and perceptual outcomes. Less is understood about how efficiently we plan sequential chunks when we switch between multiple action sequences. Do we plan learned chunks less efficiently when we switch to a different action sequence? We examined this question by comparing the initiation and execution latencies of long versus short action sequences, performed from memory, when sequences switched or repeated across trials. Additionally, each action within the sequences generated predictable perceptual outcomes that were either spatially compatible or spatially incompatible with the action sequences. Results suggested repetition costs (instead of benefits) when performing long sequences. Repetition, as opposed to switching, prolonged initiation and increased the error rate of long compared to short sequences. We attribute these results to the flexible coordination of chunk planning and execution. Repetition may prolong advanced planning of long sequences in order to resolve conflict between multiple chunks, and switching may allow the planning of later chunks to be postponed until execution. We propose that the chunking of action sequences can both facilitate and interfere with action-switching performance.

Joint scheduling and offloading of computational tasks with time dependency under edge computing networks

Mobile edge computing is an emerging technology paradigm that improves mobile devices’ computational power and efficiency by offloading computational tasks to edge servers. However, there are still some problems: (1) Ignoring the complex time dependencies of compute-intensive or latency-sensitive tasks, leading to the omission of offload scheduling opportunities for fine-grained sub-tasks within a task, thus reducing the computational power of the mobile device and the utilization of edge resources; (2) Overly biased towards optimizing task execution latency and ignoring the balance between data transmission latency and energy loss, reducing the scheme versatility in natural computing environments. Aiming at the above problems, this paper models the complex dependencies, transmission time, and execution time between computing tasks, constructs a mathematical model of the scheduling and offloading process of computing tasks, and a joint task scheduling and offloading method (N-JSU) based on Nash equilibrium is designed. This offloading strategy is divided into two steps: first, the average latency of each task is analyzed, and the scheduling order of the computational tasks is determined based on the highest response ratio of the tasks; secondly, the optimal solution is determined by iterative search to offload the most suitable IoT tasks or computing tasks to the edge server. The experimental results show that this offloading strategy can effectively reduce the latency of computationally intensive edge network tasks and improve the resource utilization of the edge server.