Execution Success Rate Research Articles

Resource allocation strategy of space cloud network based on resource clustering

SummarySpace information network (SIN) is difficult to fully utilize the limited on‐board resource due to its dynamic and heterogeneous nature, while the traditional resource management methods cannot adapt to the increasingly diverse task requirements. Space cloud network architecture is an effective technology to reduce the pressure on satellite resources. To effectively manage the space cloud network resources, we design a resources allocation strategy based on resource clustering. Firstly, we propose the space cloud network architecture. Then, we propose a genetic algorithm to cluster the space cloud resources. Finally, we propose a dynamic resource allocation method based on reinforcement learning for the dynamic characteristics of space cloud resources. The method improves the reinforcement learning algorithm through dynamic objective optimization to complete the optimization of multiple objectives in the process of space cloud resources allocation. The simulation results show that the algorithm proposed in this paper reduces the task execution delay by an average of 10.5% compared with the original DQN algorithm and increases the execution success rate by 2.17%.

EdgeOptimizer: A programmable containerized scheduler of time-critical tasks in Kubernetes-based edge-cloud clusters

Edge computing has garnered significant attention in recent years, leading to the evolution of more delay-sensitive applications towards a three-tier architecture with edge-cloud collaboration. Concurrently, technologies associated with containerization have been maturing. Notably, K8s(Kubernetes) emerges as a prominent solution for the management of extensive, dynamically evolving, and intricate container clusters. However, optimizing performance in a K8s-based architecture requires careful consideration, as intelligent algorithms cannot be easily rehearsed or retracted, and a poorly functioning algorithm can result in significant damage. To enhance the success rate of time-critical task execution in real production environments, it is crucial to provide an algorithm optimizer for service orchestration and request dispatching, especially when dealing with different services. Traditionally, building a K8s-based experimental system during the early stages of experiments has been time-consuming and involved significant programming efforts. In this paper, we introduce EdgeOptimizer, a decoupled and modularized optimizer for scheduling in multiple clusters. EdgeOptimizer also serves as an online testbed for algorithm verification in K8s-based systems, offering detailed configuration options to facilitate cluster management. By collecting system information and employing an interface-oriented system architecture, EdgeOptimizer enables users to quickly develop, deploy, and switch between various algorithms, significantly reducing the upfront costs associated with setting up an experimental environment. We evaluated the performance of EdgeOptimizer based on overall overload and demonstrated its scalability and effectiveness in verifying the efficacy of service orchestration and request dispatching algorithms for time-critical tasks. Our findings illustrate the value of EdgeOptimizer in improving the overall success rate of executing time-critical tasks, thus highlighting its potential in real-world scenarios.

Computing Task Offloading in Vehicular Edge Network via Deep Reinforcement Learning

Background: In recent years, with the development of the Internet of Vehicles, a variety of novel in-vehicle application devices have surfaced, exhibiting increasingly stringent requirements for time delay. Vehicular edge networks (VEN) can fully use network edge devices, such as roadside units (RSUs), for collaborative processing, which can effectively reduce latency. background: In recent years, with the development of the field of internet of vehicles, a variety of novel in-vehicle application devices have surfaced, exhibiting increasingly stringent requirements for time delay. Vehicular edge network (VEN) can make full use of network edge devices, such as road side unit (RSU) for collaborative processing, which can effectively reduce the latency. Objective: Most extant studies, including patents, assume that RSU has sufficient computing resources to provide unlimited services. But in fact, its computing resources will be limited with the increase in processing tasks, which will restrict the delay-sensitive vehicular applications. To solve this problem, a vehicle-to-vehicle computing task offloading method based on deep reinforcement learning is proposed in this paper, which fully considers the remaining available computational resources of neighboring vehicles to minimize the total task processing latency and enhance the offloading success rate. objective: A vehicle-to-vehicle computing task offloading method based on deep reinforce-ment learning is proposed in this paper, which fully considers the remaining available computa-tional resources of neighboring vehicles with the objective of minimizing the total task processing latency and enhancing the offloading success rate. Methods: In the multi-service vehicle scenario, the analytic hierarchy process (AHP) was first used to prioritize the computing tasks of user vehicles. Next, an improved sequence-to-sequence (Seq2Seq) computing task scheduling model combined with an attention mechanism was designed, and the model was trained by an actor-critic (AC) reinforcement learning algorithm with the optimization goal of reducing the processing delay of computing tasks and improving the success rate of offloading. A task offloading strategy optimization model based on AHP-AC was obtained on this basis. Results: The average latency and execution success rate are used as performance metrics to compare the proposed method with three other task offloading methods: only-local processing, greedy strategy- based algorithm, and random algorithm. In addition, experimental validation in terms of CPU frequency and the number of SVs is carried out to demonstrate the excellent generalization ability of the proposed method. result: The average latency and execution success rate are used as performance metrics to compare the proposed method with three other task offloading methods: only-local processing, greedy strate-gy-based algorithm and random algorithm. In addition, experimental validation in terms of both CPU frequency and the number of SVs is carried out to demonstrate the good generalization abil-ity of the proposed method. Conclusion: The simulation results reveal that the proposed method outperforms other methods in reducing the processing delay of tasks and improving the success rate of task offloading, which solves the problem of limited execution of delay-sensitive tasks caused by insufficient computational resources.

Robotic Motion Control via P300-based Brain-Computer Interface System

BCI have ignited extensive research interest in fields such as neuroscience, artificial intelligence, and biomedical engineering, as they offer an opportunity to interact directly with the external environment brain signals. Despite the immense potential for applications, practical use of BCI still faces several challenges, including equipment cost and operational complexity. This study aims to develop a Brain-Computer Interface system based on P300 visual stimuli, utilizing a low-cost, user-friendly portable Muse EEG equipment for data acquisition. We designed and implemented a P300 visual stimulator in a 3x3 grid pattern, acquire the user's EEG signals using the Muse EEG equipment, and classify the data using a SVM classifier, ultimately realizing control over robot movement. Offline experimental results demonstrated an accuracy of 84.1% for the classifier under offline stage, while online stage achieved a successful execution rate of 81.2%. These findings substantiate the feasibility and potential of using low-cost, portable devices like the Muse EEG equipment for BCI research, opening new avenues in the field.

End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function.

An end-to-end approach to autonomous navigation that is based on deep reinforcement learning (DRL) with a survival penalty function is proposed in this paper. Two actor-critic (AC) frameworks, namely, deep deterministic policy gradient (DDPG) and twin-delayed DDPG (TD3), are employed to enable a nonholonomic wheeled mobile robot (WMR) to perform navigation in dynamic environments containing obstacles and for which no maps are available. A comprehensive reward based on the survival penalty function is introduced; this approach effectively solves the sparse reward problem and enables the WMR to move toward its target. Consecutive episodes are connected to increase the cumulative penalty for scenarios involving obstacles; this method prevents training failure and enables the WMR to plan a collision-free path. Simulations are conducted for four scenarios-movement in an obstacle-free space, in a parking lot, at an intersection without and with a central obstacle, and in a multiple obstacle space-to demonstrate the efficiency and operational safety of our method. For the same navigation environment, compared with the DDPG algorithm, the TD3 algorithm exhibits faster numerical convergence and higher stability in the training phase, as well as a higher task execution success rate in the evaluation phase.

Cloud-Based Dynamic Task Scheduling and Load Balancing Using a Variety of Intelligent Schemes

One of the main problems with cloud computing is load balancing, which divides tasks into virtual machines (VMs) with varying lengths and completion times. As a result, keeping VMs loaded up during job scheduling and allocation is difficult. In this research, we suggested secure load balancing in a cloud context and resource-aware dynamic job scheduling utilizing intelligent algorithms. The process for the planned work is as follows: (1). The Human Mental Search (HMS) method is used to cluster Real-Time and Non-Real Time jobs into four categories: Real-Time and Short, Real-Time and Long, Non-Real Time and Short, and Non-Real Time and Long. (2). Knowledge of Energy and Delay Combined Tasks Tasks are planned based on task clustering, and the fuzzy VIKOR method is used to schedule them in the order of priority. (3). Security Risks aware VM Clustering, which employs the Hierarchical Agglomerative Clustering algorithm, consists of three distinct entities: a VM's information collector, which compiles data about VMs; a load monitor, which oversees the entire datacenter; and a decision maker, which assigns tasks by choosing the best VM. (4). Co-Resident assaults were stopped by the continuous-Actor-Critical-Algorithm (C- ACAL), which is used to pick the best VM. Using CloudSim, which measures performance in terms of response time, latency, resource utilization, throughput, energy consumption, and task execution success rate, the simulation is carried out.

Resource Allocation for Heterogeneous Computing Tasks in Wirelessly Powered MEC-enabled IIOT Systems

Integrating wireless power transfer with mobile edge computing (MEC) has become a powerful solution for increasingly complicated and dynamic industrial Internet of Things (IIOT) systems. However, the traditional approaches overlooked the heterogeneity of the tasks and the dynamic arrival of energy in wirelessly powered MEC-enabled IIOT systems. In this article, we formulate the problem of maximizing the product of the computing rate and the task execution success rate for heterogeneous tasks. To manage energy harvesting adaptively and select appropriate computing modes, we devise an online resource allocation and computation offloading approach based on deep reinforcement learning. We decompose this approach into two stages: an offloading decision stage and a stopping decision stage. The purpose of the offloading decision stage is to select the computing mode and dynamically allocate the computation round length for each task after learning from the channel state information and the task experience. This stage allows the system to support heterogeneous computing tasks. Subsequently, in the second stage, we adaptively adjust the number of fading slots devoted to energy harvesting in each round in accordance with the status of each fading slot. Simulation results show that our proposed algorithm can better allocate resources for heterogeneous tasks and reduce the ratio of failed tasks and energy consumption when compared with several existing algorithms.

SoDa: A Serverless-Oriented Deadline-Aware Workflow Scheduling Engine for IoT Applications in Edge Clouds

As a coordination tool, workflow with a large number of interdependent tasks has increasingly become a new paradigm for orchestrating computationally intensive tasks in large-scale and complex Internet of Things (IoT) applications. Serverless computing has also recently been applied to real-world problems at the network edge as well, primarily aimed at event based IoT applications. However, the existing workflow scheduling algorithm based on the virtual machine resource model is inefficient in ensuring the QoS (Quality of Service) of users on the serverless platform. In this paper, we design an elastic workflow scheduling framework in edge clouds called EWSF based on the serverless architecture. In addition, we propose a serverless-oriented deadline-aware workflow scheduling algorithm called SoDa. Furthermore, we implemented the EWSF prototype based on Knative and Kubernetes and integrated SoDa as the scheduling engine. The performance of SoDa has been verified on the experimental platform in comparison with six counterparts. The experiment results show that SoDa adapts to various scheduling environments and achieves better performance in terms of overall makespan and execution success rate. In the case of tight cluster resources, SoDa improves the overall makespan and success rate by 10.4% and 55%, respectively, compared with the second-best algorithm.

Latency-aware computation offloading and DQN-based resource allocation approaches in SDN-enabled MEC

The proposed mobile edge computing can transfer the computing tasks in mobile applications to the nearby edge devices, effectively reducing the processing pressure of local servers and avoiding delays in backhaul and core networks, thus better solving the problem that cloud computing cannot effectively handle resource allocation. However, the complexity of the wireless environment during the communication process leads to the fact that the computing tasks are easily caused by the increase in the number of traffic and packet loss when they are uploaded to the MEC side through the wireless link, which cannot guarantee a lower total system energy consumption and shorter total delay. To address the problem that mobile devices cannot handle many computationally intensive tasks in a timely manner, this paper proposes a task offloading optimization scheme for SDN-enabled MEC environments. Modeling the computation offloading problem based on Lyapunov optimization, and then analyzes the offloading delay with respect to the offloading gain. In order to guarantee application requirements, minimize energy consumption and latency, and better satisfy user QoS requests, this paper proposes a resource allocation strategy based on deep reinforcement learning. The strategy designs a DQN-based resource allocation algorithm to deploy a joint optimal offloading decision and resource allocation scheme in a mobile edge computing environment under the limited computational resources and the latency constraints of the computational tasks. Based on the experimental results, it is shown that the proposed task offloading strategy can reduce the overall latency; the proposed resource allocation strategy can reduce the total energy consumption and total latency of the system and improve the successful execution rate of tasks.

Ensuring Energy Efficiency When Dynamically Assigning Tasks in Virtualized Wireless Sensor Networks

Traditional non-virtualized Wireless Sensor Networks (WSNs) suffer from high deployment and maintenance costs, mainly because their applications are embedded in sensor nodes. Virtualization technologies address these challenges by allowing multiple sensing tasks to run over the same deployed WSN infrastructure. However, virtualization comes at an energy-delay cost, making it both essential and challenging to allocate physical and/or virtual resources efficiently to applications with different sensing tasks, especially for delay-sensitive applications. Our goal is to address the challenge of task assignment in virtualized WSNs while minimizing the overall energy consumption and meeting the given deadlines. After formulating the problem as an Integer Linear Programming (ILP), we propose a scalable heuristic. We evaluate the performance of our proposed heuristic in different scenarios and compare it with the optimal solution as well as a recent work from literature. The results indicate that our proposed heuristic leads close-to-optimal solutions with good performance in terms of execution time. It shows that the proposed DTA solution can not only achieve up to a 97% reduction of the execution time for small-scale scenarios, as compared to the optimal solution, but it also outperforms the existing benchmarks in terms of successful task execution rate by 100%.

5G communication resource allocation strategy based on edge computing

Aiming at the problem that most of the existing strategies cannot deal with the explosive growth of user data after the popularization of 5G communication technology, this paper proposes a 5G communication resource allocation strategy based on edge computing. First, the 5G communication network is virtualized to build mobile edge computing system with multiple mobile user equipment and multiple servers. Then, the communication model and calculation model of system are established. Besides, the optimization objectives are proposed based on this, which can minimize total user cost and maximize the success rate of task offloading and successful execution rate. Finally, the resource allocation problem is formalized and modelled as Markov model. The objective is to minimize the ratio of overall system energy consumption to task execution time and delay constraints, the optimal communication resource allocation scheme is obtained by solving it based on Q-learning algorithm. The experimental demonstration of proposed strategy is carried out based on the python simulation platform. Experimental results show that the total system cost and average delay of proposed strategy do not exceed 500 W and 1000 ms under the experimental conditions; its overall performance is better than other comparison strategies, can meet the interest requirements of users and service providers.

Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain

This letter presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off-road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous environments and thus do not need to explicitly account for terrain-vehicle interaction, or assume a set of discrete terrain classes. However, when operating on unstructured terrain, especially at high speeds, even small variations in the environment will be magnified and cause inaccurate plan execution. In this letter, to capture the complex kinodynamic model and mathematically unknown world state, we learn a kinodynamic planner in a data-driven manner with onboard inertial observations. Our approach is tested on a physical robot in different indoor and outdoor environments, enables fast and accurate off-road navigation, and outperforms environment-independent alternatives, demonstrating 52.4% to 86.9% improvement in terms of plan execution success rate while traveling at high speeds.

Multi-task allocation with an optimized quantum particle swarm method

Multi-task allocation in multi-agent systems aims to accomplish tasks efficiently and successfully, while obtaining more rewards to enhance the entire system operation at the same time. Most existing assignment methods are based on agent coalitions, which cannot balance the profit distribution and task execution success rate or ignore the coalition stability, leading to a low execution level and assignment failures. Few coalition scheduling methods exist for multi-task allocation based on a fixed agent population. In this paper, we propose an effective stability quantum particle swarm optimization (SQPSO) algorithm which includes high rewards obtaining, benefit dividing, coalition stability insuring, and a historical task mechanism for search acceleration. Secondly, we design an efficient establishment quantum particle swarm optimization (EQPSO) algorithm for coalition scheduling, which is equipped with coalition similarity judgment to reduce the coalition formation time cost. The experiment results show that SQPSO guarantees a superior coalition for every task and earlier convergence in the whole task set allocation, and EQPSO gives the optimal scheduling order which reduces the total execution time.

Multi UAV Cluster Control Method Based on Virtual Core in Improved Artificial Potential Field

In this paper, a method of multi UAV cluster control based on improved artificial potential field (APF) is proposed. The k-means method is used to integrate and optimize the attractive force between UAVs, and the concept of virtual core is introduced to realize the cluster control and adaptive formation flight of multiple UAVs. The attractive disturbance component of the target point is introduced and the backtracking-filling method is proposed to solve the local minimum problem in the APF. The repulsion force in the APF can realize obstacle avoidance and collision avoidance, and the virtual core can control the UAV cluster to fly to the target point under the attractive force of potential field, so as to realize the track planning and multi aircraft cooperative task. In the process of cluster flight when the UAV fails, merges or dispatches, the method can realize cluster reconfiguration and the cluster control effect and task execution success rate can be improved. The simulation experiments in virtual APF and urban environment APF show the effectiveness of this method.

Multi Level SLA Violation Based Resource Allocation in Cloud using Kernel Fuzzy C Means with Aid of EABC

In our proposed work we are considering four types of agent such as monitoring agent, coordinator agent, user agent and violation agent. Initially, user agent wants to generate the resource in cloud based on the SLA properties and coordinator agent is verifying the request type and SLA properties. The violation of the SLA is a major aspect of cloud computing and the violation leads to the reduction of customer satisfaction level and further affects the cloud provider leading to penalty. Initially the available resources are grouped by kernel fuzzy C means clustering algorithm (KFCM). Then monitoring agent report the resource list to the coordinator agent. Based on the resource list, the coordinator agent allocates the optimal resource with the help of enhanced artificial bee colony algorithm. The performance of the proposed work is evaluated by profit, penalty, cost, execution time and successful execution rate.

IMPLEMENTASI KEBIJAKAN MENTERI AGRARIA DAN TATA RUANG TENTANG PERCEPATAN PELAKSANAAN PENDAFTARAN TANAH SISTEMATIS LENGKAP DI KOTA BANDUNG

This research aims to know the strategy of the Government in the implementation of the programme of PTSL and to find out how big a success rate of Program execution PTSL in Bandung. The results showed that the Government strategy of Bandung Bandung in BPN through program implementation through the preparation of PTSL ripe includes socialization, the determination of the location, planning effort, and the establishment of the Committee ajudikasi acceleration, training and outreach. The success rate of execution of PTSL in Bandung from the target amount of the targeted land certificate 93,000 just 7,234 certificates or reached only 7.78% of the data that researchers get. This is caused by a number of working groups, the situation is not comparable with the volume so that the targets set in the achievement of the targets still not be met.

Incentive-aware virtual machine scheduling in cloud computing

As cloud computing is a market-oriented utility, optimal virtual machine (VM) scheduling in cloud computing should take into account the incentives for both cloud users and the cloud provider. However, most of existing studies on VM scheduling only consider the incentive for one party, i.e., either the cloud users or the cloud provider. Very few related studies consider the incentives for both parties, in which the cost, one of the most attractive incentives for cloud users, is not well addressed. In this paper, we investigate the problem of VM scheduling in cloud computing by optimizing the incentives for both parties. The problem is formulated as a multi-objective optimization model, i.e., maximizing the successful execution rate of VM requests and minimizing the combined cost (incentives for cloud users), and minimizing the fairness deviation of profits (incentive for the cloud provider). The proposed multi-objective optimization model can offer sufficient incentives for the two parties to stay and play in the cloud and keep the cloud system sustainable. A heuristic-based scheduling algorithm, called cost-greedy dynamic price scheduling, is then developed to optimize the incentives for both parties. Experimental results show that, compared with some popular algorithms, the developed algorithm can achieve higher successful execution rate, lower execution cost, smaller fairness deviation and most important, higher degree of user satisfaction in most cases.

Robust Execution of Probabilistic Temporal Plans

A critical challenge in temporal planning is robustly dealing with non-determinism, e.g., the durational uncertainty of a robot's activity due to slippage or other unexpected influences. Recent advances show that robustness is a better measure of solution quality than traditional metrics such as flexibility. This paper introduces the Robust Execution Problem for finding maximally robust dispatch strategies for general probabilistic temporal planning problems. While generally intractable, we introduce approximate solution techniques — one that can be computed statically prior to the start of execution with robustness guarantees and one that dynamically adjusts to opportunities and setbacks during execution. We show empirically that our dynamic approach outperforms all known approaches in terms of execution success rate.

Parallel Computing Aspects in Improved Edge Cover Based Graph Coloring Algorithm

Objective: To improve the Edge Cover based Graph Coloring Algorithm (ECGCA) using independent set by incorporating parallel computing aspects in algorithm. Finding optimum time complexity is one of the main objectives of this paper. Methods/Statistical Analysis: This paper introduced some modification in ECGCA. Algorithm is implemented and tested using Java programming language. Java multithreading concept is used to achieve parallel computing in algorithm. DIMACS graph instances are used to test algorithm. Finding: Algorithm is tested on more than 75 DIMACS graph instances. To analyze the time complexity, execution time of algorithm in seconds is calculated by program. Algorithm is tested on different DIMACS graph instances. Test data is analyze in this paper and found that proposed algorithm executed in optimum time for large graphs. This paper also compared parallel algorithm and found that proposed parallel algorithm is less time complex than sequential algorithm. Most of the exact graph coloring algorithms are not suitable for large graph (more than 100 vertices) but proposed algorithm is tested on many large graphs and high execution success rate of algorithm is achieved. Application: This paper shows the experimental results of different type of application data. It means this algorithm can be used for maximum types of applications.

Redundant and fault-tolerant algorithms for real-time measurement and control systems for weapon equipment

Because of the high availability requirements from weapon equipment, an in-depth study has been conducted on the real-time fault-tolerance of the widely applied Compact PCI (CPCI) bus measurement and control system. A redundancy design method that uses heartbeat detection to connect the primary and alternate devices has been developed. To address the low successful execution rate and relatively large waste of time slices in the primary version of the task software, an improved algorithm for real-time fault-tolerant scheduling is proposed based on the Basic Checking available time Elimination idle time (BCE) algorithm, applying a single-neuron self-adaptive proportion sum differential (PSD) controller. The experimental validation results indicate that this system has excellent redundancy and fault-tolerance, and the newly developed method can effectively improve the system availability.