Resource Utilization Of Nodes Research Articles

An enhanced whale optimization algorithm for task scheduling in edge computing environments.

The widespread use of mobile devices and compute-intensive applications has increased the connection of smart devices to networks, generating significant data. Real-time execution faces challenges due to limited resources and demanding applications in edge computing environments. To address these challenges, an enhanced whale optimization algorithm (EWOA) was proposed for task scheduling. A multi-objective model based on CPU, memory, time, and resource utilization was developed. The model was transformed into a whale optimization problem, incorporating chaotic mapping to initialize populations and prevent premature convergence. A nonlinear convergence factor was introduced to balance local and global search. The algorithm's performance was evaluated in an experimental edge computing environment and compared with ODTS, WOA, HWACO, and CATSA algorithms. Experimental results demonstrated that EWOA reduced costs by 29.22%, decreased completion time by 17.04%, and improved node resource utilization by 9.5%. While EWOA offers significant advantages, limitations include the lack of consideration for potential network delays and user mobility. Future research will focus on fault-tolerant scheduling techniques to address dynamic user needs and improve service robustness and quality.

A Deep Sensing System for Monitoring the Health Status of Transmission Line Equipment Based on Self-Powered Sensors

The increasingly complex transmission lines can no longer rely on a single manual inspection method to monitor the health of equipment. Considering the actual needs and conditions, online monitoring of transmission lines can make up for the shortcomings of traditional detection methods. In order to reduce the manual workload and improve the accuracy and efficiency of detection, this paper introduces the application of self-powered sensors in the transmission line equipment health state depth sensing system. The research considers that the sensor is the important sensor module foundation of the online monitoring system. The characteristics of sensor cells used for solar energy conversion are analyzed. The self-powered sensor is introduced into the transmission line equipment health depth sensing system, and the transmission line network model and data transmission compression algorithm are optimized. The experimental results show that photovoltaic cells can effectively provide stable and relatively sufficient power for sensors, and prolong the service life of nodes. This improves the utilization of node resources, effectively reduces latency and energy consumption, and effectively extends the application life cycle of the sensor system.

An intelligent Hybrid‐Q Learning clustering approach and resource management within heterogeneous cluster networks based on reinforcement learning

AbstractRecently, heterogeneous cluster networks (HCNs) have been the subject of significant research. The nature of the next‐generation HCN environment is decentralized and highly dynamic; optimization techniques cannot quite express the dynamic characteristics of node resource utilization and communication of HCN networks. In this article, we present an intelligent Hybrid‐Q Learning approach (Hybrid QL)‐based clustering approach for IoT and WSN. Using the self‐learning abilities of (HCNs), we propose a model for dynamic accessing systems on nodes and agents that identify the best possible paths and communication over heterogeneous cluster networks using reinforcement learning. In addition to reducing energy consumption, it creates efficient and effective resource utilization and node communication performance. Through increased throughput and link management, the HCN aims to reduce energy consumption. The proposed model is compared to existing approaches based on various scenarios. Finally, the results of the evaluation tasks demonstrate high accuracy, low‐level complexity, fast dynamic response times, and scalability for heterogeneous cluster networks. Our model showed exceptional node allocation efficiency for dynamic IOT environments and WSNs.

Resource and delay aware fine-grained service offloading in collaborative edge computing

Fine-grained service offloading in collaborative edge computing can realize full use of the limited resources of edge nodes to achieve efficient parallel computing. The existing research mainly focuses on service delay but pays insufficient attention to the network status, which will easily cause unbalanced resource utilization. Therefore, we propose a resource and delay aware fine-grained service offloading mechanism. First, we propose a novel network-adaptive service graph reconstruction algorithm to reduce the complexity of service offloading and the transmission delay, which includes service graph partition, dependency conflict detection and elimination, and service graph re-creation. Next, to better balance link and node resource utilization respectively, we propose original graph-based and association graph-based service graph mapping algorithms based on graph neural networks. A goal-directed affinity-based loss function is explored for them, which aims to address the difficulty of label generation in supervised learning. We conduct extensive simulation experiments with different numbers of subtasks, edge nodes and service requests under different network resource statuses. The experimental results show that the proposed service graph reconstruction method can balance network resource utilization, while reducing the service transmission delay and algorithm execution time for complex services. Moreover, the service graph mapping algorithms can improve the resource utilization balance degree while satisfying service constraints with start-end node location, resources and delay in various scenarios, especially in the case of unbalanced user distribution. Generally, our fine-grained service offloading mechanism enables short execution time and strong scalability, and is applicable to dynamic edge networks.

Multiagent-Based Modeling and Simulation of a Coal Multimodal Transport System

With the change in coal supply and demand, the dynamics of multiple transit nodes and the connection between different transportation modes make the Coal Multimodal Transportation System (CMTS) more complicated in the long-distance transportation of coal. Therefore, it is necessary to analyze the multimodal transportation nodes, build a coal multimodal transportation model, measure the network throughput through simulation experiments, and identify system bottlenecks. The CMTS is a complex nonlinear dynamic system with many participants with complex and uncertain links. Different transportation modes, operation links, and connection processes will affect system performance, and modeling and simulation technology effectively study complex dynamic systems. This paper takes the CMTS as the research object, uses agent-based modeling methods and Witness simulation software to analyze the composition and operation mechanism of CMTS, establishes the multiagent model of CMTS, and validates the model by a Witness simulation experiment of northern coal shipped to south. The simulation results indicate the capacity of the transport route and resource utilization of nodes in CMTS in case of different demand growth rates in the future. Based on the multiagent model andWitness simulation results, this paper provides practical support for constructing and applying the multimodal transport system model library and provides the basis for decision-making for the CMTS plan.

Smart Healthcare: RL-Based Task Offloading Scheme for Edge-Enable Sensor Networks

With the wide application of Internet-of-Medical-Things (IoMTs) or sensor nodes which equipped with sensors. These networked sensors are used to gather enormous data from different smart healthcare applications, and this collected data process for making appropriate decisions. Edge computing is an efficient platform that provides computational resources to collect sensor data. In the meantime, intelligent and accurate resource management by Artificial Intelligence (AI) has become the center of attention, especially in healthcare systems. With the help of AI, IoMT based healthcare devices will remarkably enhance the computational speed and range. But the challenging issue in these energy-hungry, short battery life, and delay intolerant portable devices is inappropriate and inefficient classical trends of fair resource allotment. Thus, this paper proposes Computation Offloading using Reinforcement Learning (CORL) scheme to minimize latency and energy consumption. We first formulate the problem as a combined latency and energy cost minimization problem, satisfying the lack of limited battery capacity and service latency deadline constraints. Moreover, proposed algorithm search optimal available resources node to offload task towards the trade-off between energy and latency. The experimental results show the benefits of the proposed scheme in terms of saving energy, minimizing latency, and maximum utilization of node resources in edge-enabled sensor networks. We are using an iFogSim simulator to validate the proposed scheme under realistic assumptions.

RETRACTED: A Global Optimal Mapping Method of Network based on Discrete Optimization Firefly Algorithm

In order to solve the current network rigidity and optimize the resource requirements of multiple virtual networks for synchronous mapping, improve the success rate of virtual network mapping requests, the long-term revenue and overhead ratio of the substrate network, node resource utilization rate and link resource utilization rate. A global optimal mapping method based on discrete optimization firefly algorithm is presented. Analyze the problem of virtual network mapping, map virtual nodes to physical nodes, and map virtual links to physical paths. According to the resource constraints of the virtual network and the substrate network, a multi-objective optimization model of the virtual network mapping is constructed, and the discrete fireflies optimization algorithm is used to obtain the global optimal solution of the virtual network mapping model to achieve the optimal allocation of global resources. The experimental results show that the discrete optimization firefly algorithm has a good performance in solving the virtual network mapping problem, and can effectively improve the virtual network request acceptance rate, node resource utilization rate, link resource utilization rate, and long-term revenue and cost ratio of the substrate network, ensuring Optimization of virtual network resources.

Enhanced QoS Multicast Routing Protocol in MANETs using Trust and Load Balance

Mobile ad-hoc network (MANET) is a wireless networks without fixed infrastructure, where each node can interact with its one hop distance neighbors only. Since the nodes are continuously moving from one location to another location, the network topology is not constant. Provisioning of Quality of Service (QoS) in MANETs is a challenging task because of its unstable nature. In multicast routing protocol, a sender node is sending the data to the group of members (multiple destination nodes), where the intermediate nodes resources are consumed at higher rate. In this paper, utilization of node resources (QoS parameters) is minimized by considering node attitude (trust) and load balancing. Here node energy and link bandwidth are considered as the QoS parameters. The proposed method "Enhanced QoS Multicast Routing Protocol in MANETs Using Trust and Load Balance-QMTL" identifies the intermediate nodes with higher trust values and constructs the multicast tree with optimized load balance. The performance of proposed method is analyzed theoretically (using asymptotic notations) and practically (using simulation tool-ns2)..

K‐PSO: An improved PSO‐based container scheduling algorithm for big data applications

SummaryIn recent years, Docker container technology is being applied in the field of cloud computing at an explosive speed. The scheduling of Docker container resources has gradually become a research hotspot. Existing big data computing and storage platforms apply with traditional virtual machine technology, which often results in low resource utilization, a long time for flexible scaling and expanding clusters. In this paper, we propose an improved container scheduling algorithm for big data applications named Kubernetes‐based particle swarm optimization(K‐PSO). Experimental results show that the proposed K‐PSO algorithm converges faster than the basic PSO algorithm, and the running time of the algorithm is cut in about half. The K‐PSO container scheduling algorithm and algorithm experiment for big data applications are implemented in the Kubernetes container cloud system. Our experimental results show that the node resource utilization rate of the improved scheduling strategy based on K‐PSO algorithm is about 20% higher than that of the Kube‐scheduler default strategy, balanced QoS priority strategy, ESS strategy, and PSO strategy, while the average I/O performance and average computing performance of Hadoop cluster are not degraded.

Adaptive path splitting based survivable virtual network embedding in elastic optical networks

Abstract Virtualization facilitates heterogeneous cloud applications to share the same physical infrastructure with admirable flexibility, while resource efficiency and survivability are critical concerns for virtual network embedding (VNE). In this paper, we study two-stage coordinated survivable VNE (SVNE) problem and propose an adaptive path splitting based SVNE (APSS) scheme for elastic optical networks (EONs). For APSS, we first develop a concise anchor node strategy to balance the node resource utilization and restrict the solution space of the candidate substrate nodes, which coordinates node mapping with link mapping to limit the distance spans of the virtual links. Then, we employ an adaptive path splitting policy to provide full protection against single-link failures with partial backup resource, and design an agile frequency slot windows choosing mechanism to mitigate the spectrum fragmentation for link resource efficiency. We evaluate the proposed APSS scheme and compare its performances with some counterpart schemes. Simulation results demonstrate that the proposed APSS scheme can achieve satisfactory performance in terms of spectrum utilization and blocking ratio, even if with higher backup redundancy ratio.

Resource Usage Evaluation Study in HPC Cluster

In order to evaluate the running state of computing clusters, this paper proposes a measure index for evaluating the resource utilization of nodes in high-performance computing clusters -- Load Score of Computing Node(LSCN), and compares two methods for determining parameter weights, principal component analysis (PCA) and entropy weight determination method (EWD), in combination with relevant algorithms in the field of machine learning, so as to provide useful guidance for the running and maintenance of computing clusters.

Incorporating energy and load balance into virtual network embedding process

Virtual network embedding has propounded as one of the most important techniques to address the issue of Internet architecture ossification. Previous studies on virtual network embedding algorithms focus primarily on the revenue of service providers (SPs) and the acceptance ratio of virtual network requests (VNRs), regardless of the energy consumption for substrate nodes and substrate links. To deal with this issue, some of researchers proposed energy-aware virtual network embedding algorithm to do a tradeoff between the revenue and energy consumption. However, the problem of virtual network embedding is a multi-objective optimization problem, which should take into account the multiple factors such as revenue, energy consumption, quality of services (QoS), load balancing of nodes and links, and so on. In this paper, we incorporate node energy consumption and node resource utilization into the embedding potential computation for substrate nodes, and propose a comprehensive node ranking method called CNRM to measure the substrate node importance. In addition, we utilize an improved differentiated pricing strategy to assign different weights to substrate links according to their resource utilization ratios, adopt the shortest path algorithm to select substrate path with the minimum energy consumption for virtual link during the link mapping process. Extensive simulation results demonstrated that our algorithm achieves a better tradeoff among the acceptance ratio, revenue/cost ratio, energy consumption and network load balance.

TSTE: A Time-variant Stochastic Trust Evaluation Model in Social Networks

Building appropriate trust evaluation models is an important research issue for security guarantee in social networks. Most of the existing works usually consider the trust values at the current time slot, and model trust as the stochastic variable. However, in fact, trust evolves over time, and trust is a stochastic process. In this paper, we propose a novel time-variant stochastic trust evaluation (TSTE) model, which models trust over time and captures trust evolution by a stochastic process. Based on the proposed model, we derive the time-variant bound of untrustworthy probability, which provides stochastic trust guarantee. On one hand, the time-variant trust level of each node can be measured by our model. Meanwhile, by tolerating nodes with relatively poor performance, our model can effectively improve the node resource utilization rate. Numerical simulations are conducted to verify the accuracy and consistency of the analytical bounds on distinguishing misbehaved nodes from normal ones. Moreover, simulation results on social network dataset show the tradeoff between trust level and resource utilization rate, and verify that the successful transmission rate can be improved by our model.

A Performance Study of Discrete-Error-Checking Scheme (DECS) with the Optimal Division Locations for IEEE 802.16-Based Multihop Networks

In IEEE 802.16 specifications, a CRC field can be attached in the rear of a WiMAX MPDU. Thus, each intermediate node (relay node or base station) in an 802.16-based multihop network can perform error detection on a received WiMAX MPDU. On the sender, the ARQ mechanism will be enabled to retransmit the MPDU if a transmission error occurs and an ACK message cannot be received. However, the ARQ mechanism is unsuitable for real-time traffic due to the delay consideration and the CRC field becomes an option to reduce the overhead of a WiMAX MPDU. Once the CRC field is removed from a WiMAX MPDU, the error occurrence cannot be detected by the intermediate nodes in time, and the erroneous data is still forwarded in the network but discarded by the destination. The resources of nodes in a network are wasted. Hence, the error detection mechanism should be retained for real-time traffic, but the overhead of CRC should be reduced. In this paper, we study an efficient discrete-error-checking scheme (DECS) to reduce the CRC overhead for real-time traffic. The DECS only needs several CRC checking bits, which are attached behind some WiMAX MPDUs. The DECS can efficiently provide the error detection for the intermediate nodes to discard these erroneous and useless data early. Thus, the utilization of node resources and wireless bandwidth can be improved significantly.