Load Balancing Rate Research Articles

Effective Workflow Scheduling in Cloud using Constriction Factor based Inertia Weight Particle Swarm Optimization

Cloud computing allows rapid provision of resources based on the need. This enables users to execute the independent tasks and dependent tasks called workflows on the cloud system. Workflow scheduling is a crucial problem that is NP Hard and is still a challenging problem. Particle Swarm Optimization (PSO) is one of the commonly used metaheuristic algorithms for solving task scheduling problems, but it has issues with premature convergence and lack of diversity. In recent years, chaotic maps have been employed in PSO to enhance its performance. This study proposes a Constriction factor-based inertia weight in PSO for workflow scheduling (CFPSO). The proposed algorithm utilizes a constriction factor for updating the inertia weight, which enhances the exploration ability of the algorithm thereby avoid local optima. The algorithm considers a fitness function with an aim to minimize makespan, service cost, and maximize load balance. The proposed algorithm is evaluated using a set of benchmark workflows, and the obtained results are compared with the standard PSO algorithm, Grey Wolf Optimizer (GWO) algorithm and Chaotic PSO algorithm. The extensive experimentation performed show that the proposed algorithm outperforms the other algorithms in terms of makespan, service cost, and load balance. The proposed CFPSO shows reduction of 20% of makespan, 2% of the service cost and 18% load balance rate compared to the conventional algorithms on Montage workflow with 1000 tasks. The use of constriction factor enhances the performance of the algorithm and makes it suitable for solving complex problems with multiple objectives. The proposed algorithm can be used in real-world applications to optimize workflow scheduling in cloud computing environments.

Fractional Political Optimizer-Based Switch Migration in Software-Defined WAN for Load Balancing with Deep Q Network

In order to address the load imbalance problem, a successful technique known as Fractional Political Optimizer (FPO)-based switch migration is modeled. The suggested FPO is created by integrating the Political Optimizer (PO) with Fractional Calculus (FC). DQN receives the controller’s initial load value in order to generate the anticipated load. By calculating the load value based on CPU utilization, controller maximum capacity, and input packet volume, load imbalance issues are identified. Switch migration is carried out using FPO based on fitness measure, which takes into account migration factors, such as migration cost, projected load, controller capacity, and load balancing rate (LBR). To complete the switch migration procedure, the load on the controller is assessed using the data packets and a threshold value. For the NSFNet topology, the proposed FPO-based switch migration approach achieved the following results: 17.286 kbps, 0.1191 s, 48.797, −0.238, 0.1231 s, and 5.0391 kbps, respectively.

Convergence time aware switch migration algorithm for SDN (CTSMA) cloud datacenter

Multi-controller deployment in a software-defined network improves the system's stability and scalability. However, since network traffic fluctuates, it presents a new problem for balancing loads on remote controllers. Controller Adaption and Migration Decision (CAMD) and Dynamic and Adaptive Load Balancing (DALB) frameworks are developed for efficient balancing of load on the controller to solve the problem of controller overload due to dynamic network traffic. CAMD was considered to be more efficient than DALB, but when the network is more dynamic, and the incoming traffic flow is elephant flow this leads to the overall reduction in system performance. This study proposed a Convergence Time aware Switch Migration Algorithm (CTSMA) that solved the network challenge when the network is more dynamic and incoming traffic flow is more. This research developed an enhanced switch migration algorithm to address the network difficulty of dynamically changing incoming load. Because of the imbalanced distribution of load on the controllers, processing flows will have longer response times and the controllers' throughput will be reduced. Switch migration is the best method of resolving the issue. Present techniques, on the other hand, focus solely on load balancing performance while ignoring migration efficiency, thereby leading to large migration costs and excessive control overheads. To increase the load and migration efficiency of controllers, this research work developed a convergence time aware switch migration method. To find the group of underloaded controllers in the network, the improved framework looked at controller volatility and average load status. Performance comparison indicators included controller throughput, reaction time, and convergence time. According to simulation studies, CTSMA outperforms CAMD by cutting controller reaction time by roughly 6.1%, increasing controller throughput by 8.0% on average, keeping a decent load balancing rate, lowering migration costs, and maintaining the best load balancing rate.

MODECP: A Multi-Objective Based Approach for Solving Distributed Controller Placement Problem in Software Defined Network.

Software-Defined Network is an emerging networking paradigm that enables intelligent and flexible network management. Specifically, the design of the control plane is crucial. Therefore, in order to avoid a single point of failure, multiple controllers are deployed constantly in a distributed manner on the control plane. In this paper, we propose a controller placement approach based on multiple objectives (MODECP), including network delay, network security, load-balancing rate, and link occupancy. In the controller placement stage, an improved multi-objective differential evolution algorithm is proposed to search for controllers’ positions and assign switches to controllers reasonably. Furthermore, an improved affinity propagation algorithm is proposed to obtain the number of controllers placed in the network partition stage, comprehensively considering the delay, node security, and load. Simulations are performed based on several topologies from Internet Topology Zoo. Extensive results show that the proposed algorithm can realize trade-offs among multiple objectives and improve network performance in delay, security, controller load, and link occupancy compared to the single-objective based approach. Moreover, compared with the genetic algorithm and random placement algorithm, the proposed algorithm performs better with low latency, high security, low load rate, and low link overhead.

DSMLB: Dynamic switch-migration based load balancing for software-defined IoT network

The deployment of multiple controllers in Software-Defined Internet of Things (SD-IoT) networks enhance the distributed control plane scalability and reliability. With the rapid advancement of IoT, millions of smart devices generate enormous amounts of IoT traffic, causing significant challenges for the network to acquire the better Quality-of-Service (QoS) to the user. The control plane load management is crucial due to the dynamic nature of IoT networks and the heterogeneity of IoT devices in terms of flow generation rate. The load distribution among SD-IoT controllers relies on their available capacity to ensure optimal load balancing performance. The dynamic switch migration method was proposed in prior findings to handle load balancing distribution among controllers. However, the migration efficiency of conventional approaches is limited due to inefficient load balancing performance of the control plane after the migration of switch, leading to additional migration overhead on the network. Taking this into account, we propose a dynamic switch migration-based load balancing approach (DSMLB) to prevent control plane overhead and distribute traffic efficiently while considering heterogeneous IoT devices. The proposed DSMLB scheme measures the real-time load ratio to the mean load ratio of each controller by describing various load metrics and selecting the target controller by optimizing the migration efficiency with residual controller resource utilization. When choosing the candidate switches from the associated overloaded controller, DSMLB considers the migration efficiency and load balancing degree simultaneously for the fastest load reduction and enhances the load balancing performance. The simulation results show that DSMLB outperforms conventional approaches for efficient load balancing performance on a distributed control plane by reducing the controller response time up to 38.6% and migration cost about 45.5% on average. Moreover, DSMLB also improves controller load balancing rate and reduces communication overhead.

Load Balancing Using Dynamic Ant Colony System Based Fault Tolerance in Grid Computing

Load balancing is often disregarded when implementing fault tolerance capability in grid computing. Effective load balancing ensures that a fair amount of load is assigned to each resource, based on its fitness rather than assigning a majority of tasks to the most fitting resources. Proper load balancing in a fault tolerance system would also reduce the bottleneck at the most fit resources and increase utilization of other resources. This paper presents a fault tolerance algorithm based on ant colony system, that considers load balancing based on resource fitness with resubmission and checkpoint technique, to improve fault tolerance capability in grid computing. Experimental results indicated that the proposed fault tolerance algorithm has better execution time, throughput, makespan, latency, load balancing and success rate.

Dynamic Resource Allocation Using Improved Firefly Optimization Algorithm in Cloud Environment

ABSTRACT Today, cloud computing has provided a suitable platform to meet the computing needs of users. One of the most important challenges facing cloud computing is Dynamic Resource Allocation (DSA), which is in the NP-Hard class. One of the goals of the DSA is to utilization resources efficiently and maximize productivity. In this paper, an improved Firefly algorithm based on load balancing optimization is introduced to solve the DSA problem called IFA-DSA. In addition to balancing workloads between existing virtual machines, IFA-DSA also reduces completion time by selecting appropriate objectives in the fitness function. The best sequence of tasks for resource allocation is formulated as a multi-objective problem. The intended objectives are load balancing, completion time, average runtime, and migration rate. In order to improve the initial population creation in the firefly algorithm, a heuristic method is used instead of a random approach. In the heuristic method, the initial population is created based on the priority of tasks, where the priority of each task is determined based on the pay as you use model and a fuzzy approach. The results of the experiments show the superiority of the proposed method in the makespan criterion over the ICFA method by an average of 3%.

A hybrid elephant herding optimization and harmony search algorithm for potential load balancing in cloud environments

In cloud computing environment, load balancing delinquent arises when a large count of new IoT user requests are linked with specific fog nodes. So, a well-organized load balancing tactic is needed in cloud computing. Therefore, in this manuscript, a hybrid elephant herding optimization and harmony search algorithm (HSA) for potential load balancing in cloud environments (HEHO-HSA-PLB-CE) is effectively proposed for reducing task waiting time, load balancing rate, scheduling time, delay and energy consumption. The HEHO algorithm and HSA are mainly used for leveraging the allocation of virtual machine (VM) and incorporating an enhanced strategy of physical machine selection. The proposed HEHO-HSA-PLB-CE method aims at preventing the issue of premature convergence or the issue related to the solution falling at the point of local optimum. Finally, the proposed method potentially achieves load balance under the allocation of VM and enhancement of resource utilization in the cloud computing environment. The proposed approach is activated in CloudSim and the efficiency of the proposed method is assessed by evaluation metrics, such as response time, load balance rate, scheduling time, delay, energy consumption. Then, the simulation performance of the proposed method provides lower delay 32.82%, 25.32%, 29.34% and 34.18%, low energy consumption 38.22%, 25.46%, 42.12% and 15.34% compared with the existing methods, like Aquila optimizer for PLB in CE (AO-PLB-CE), arithmetic optimization algorithm for PLB in CE (AOA-PLB-CE), sine cosine algorithm for PLB in CE (SCA-PLB-CE), and enhanced krill herd algorithm for PLB in CE (EKHO-PLB-CE) respectively.

Enhancing investigations in data migration and security using sequence cover cat and cover particle swarm optimization in the fog paradigm

In recent years, fog and mobile edge computing have grown rapidly due to the large amount of data generated by the Internet of Thing (IoT) devices. It provides a variety of services within the end user IoT environment, but suffers from inefficient scheduling, which results in more significant delays than cloud computing. In this research we propose a data migration procedure that beats the metrics of delay, response time, and load balancing rate in the fog computing paradigm. It is possible to reduce the amount of replicated and integrated data by using Sequence Cover Cat Swarm Optimization (SCCSO) and Sequence Cover Particle Swarm Optimization (SCPSO) by using appropriate Virtual machines (VMs) which lock highly used machines and give service to low used machines in cloud communication storage.; this allows us to obtain resources efficiently in the fog environment. After being tested in the iFogsim climate, The protocols performed better in the iFogsim climate in terms of response time, scheduling time load balancing rate and delay than the other scheduling algorithms.

Demming regressive multiobjective dragonfly optimized controller placement in SDN environment

Wireless networks are of high significance in current telecommunication systems, and in order to improve these systems, Software-Defined Networks (SDN)is used to centrally monitor and control the whole network with the help of a controller. The design of an SDN-based network is needed to identify the optimal amount of controllers for improving performance of network. Controller placement problem is determined on propagation latency but it failed to consider the load balancing, fault tolerance, bandwidth consumption and data transmission rate. Plan to develop a novel technique called Demming Regressive Multiobjective Dragonfly Optimized Controller Placement (DRMDOCP) for an optimal number of controller placement for enhancing network performance during different topologies. By applying DRMDOCP, the optimum number of controllers are selected and placed into the network to improve the overall networks performance. Therefore, delay minimization-based controller placement strategy is extremely preferred. The simulation of DRMDOCP technique and existing methods is conducted using network topology dataset and different performance metrics. The simulation results demonstrate that the DRMDOCP increases the packet delivery, throughput and reduces the average latency, packet drop when compared to state-of-the-art method.

CAVMS: Application-Aware Cloudlet Adaption and VM Selection Framework for Multicloudlet Environment

The mobile users offload the application to nearby cloudlet servers instead of the remote cloud for better end-user experience. Each cloudlet is able to process real-time applications with the help of virtual machines (VM). While multiple applications running on the cloudlet, the possibility of overprovisioning issue is unavoidable due to massive task-offloading requests from mobile devices. In this regard, balancing the load, among the cloudlets in a high-interactive applications scenario, is a promising issue. In order to balance the cloudlet load, migration of VMs from an overloaded cloudlet to an underloaded cloudlet is a favored solution. During this process, a well-designed migration mechanism must be outlined that can perform two steps such as VM selection and cloudlet adaption. In this article, an application-aware cloudlet adaption and VM selection framework has been devised for balancing the load in a multicloudlet environment. The candidate-cloudlet adaption is based on a migration efficiency indicator that reduces the response time and enhances load-balancing rate. Furthermore, the effectiveness of the framework has been evaluated by comparing with other state-of-the-art cloudlet-selection strategies.

An efficient interval many-objective evolutionary algorithm for cloud task scheduling problem under uncertainty

Task scheduling is an important research direction in cloud computing. The current research on task scheduling considers mainly the design of scheduling strategies and algorithms and rarely gives attention to the influences of uncertain factors, such as the network bandwidth and millions of instructions per second (MIPS), on the scheduling process. The network bandwidth and MIPS directly affect the performance of a virtual machine (VM), which further influences the scheduling performance. In this paper, uncertain factors are transformed into interval parameters. The make-span, scheduling cost, load balance, and task completion rate are simultaneously considered in the scheduling process. Then, an interval many-objective cloud task scheduling optimization (I-MCTSO) model is designed to simulate real cloud computing task scheduling. To implement this model, an interval many-objective evolutionary algorithm (InMaOEA) is proposed. An interval credibility strategy is employed to improve the convergence performance. The hyper-volume and degree of overlap based on the interval congestion distance strategy are used to increase the population diversity. Simulation results demonstrate the effectiveness and superior performance of InMaOEA in comparision with other algorithms. The proposed approaches can provide decision-makers with an efficient allocation plan for cloud task scheduling.

Multi-criteria decision-making for controller placement in software-defined wide-area networks

Software-defined networks have many benefits such as more control over the control plane and reduced operating costs through separating the control plane from the data plane in network equipment. One of the most critical problems in software-defined networks is a controller placement problem, which significantly influences its overall performance. The purpose of this problem is to determine the number of controllers required and how to assign switches. This paper attempts to solve this problem, aiming to reduce the network's operational cost and to improve their survivability and load balancing. Hence, we have tried to divide the network into several subdomains using segmentation. Then, we used multi-criteria decision-making methods to solve the controller placement in each subdomain. For this purpose, we considered criteria such as reliability rate, cost, delay, and processing capacity. To assign switches to controllers, we used the proposed mathematical model to minimize the objective function while observing the defined constraints. Furthermore, according to the proposed architecture, we used distance to the central controller, adjacent neighborhood, and controller memory to select the cluster head controller for each subdomain to communicate with the central controller. Finally, we performed experiments on topologies Uran, SwitchL3, and Sinet of the Internet Topology Zoo to evaluate the proposed method. In these experiments, we compared the results of the proposed method with our work-related methods, including Controller Placement Analytic Hierarchy Process (CPAHP) and Controller Placement Modified Density Peak (CPMDP), in terms of criteria such as cost, survivability, number of controllers, connection failure probability, average delay, and controller load-balancing rate. The results show that the proposed method outperforms CPMDP and CPAHP. Thus, the proposed method has a 24.97% and 19.76% improvement in reducing network implementation costs than CPMDP and CPAHP, respectively.

Research on Fog Resource Scheduling based on Cloud-fog Collaboration Technology in the Electric Internet of Things

Background: With the further development of the electric Internet of Things (eIoT), IoT devices in the distributed network generate data with different frequencies and types. Objective: Fog platform is located between the smart collected terminal and cloud platform, and the resources of fog computing are limited, which affects the delay of service processing time and response time. Methods: In this paper, an algorithm of fog resource scheduling and load balancing is proposed. First, the fog devices divide the tasks into high or low priority. Then, the fog management nodes cluster the fog nodes through the K-mean+ algorithm and implement the earliest deadline first dynamic (EDFD) task scheduling algorithm and De-REF neural network load balancing algorithm. Results: We use tools to simulate the environment, and the results show that this method has strong advantages in -30% response time, -50% scheduling time, delay, -50% load balancing rate, and energy consumption, which provides a better guarantee for eIoT. Conclusion: Resource scheduling is an important factor affecting system performance. This article mainly addresses the needs of eIoT in terminal network communication delay, connection failure, and resource shortage. A new method of resource scheduling and load balancing is proposed. The evaluation was performed, and it proved that our proposed algorithm has better performance than the previous method, which brings new opportunities for the realization of eIoT.

The Application of Fractal Transform and Entropy for Improving Fault Tolerance and Load Balancing in Grid Computing Environments

This paper applies the entropy-based fractal indexing scheme that enables the grid environment for fast indexing and querying. It addresses the issue of fault tolerance and load balancing-based fractal management to make computational grids more effective and reliable. A fractal dimension of a cloud of points gives an estimate of the intrinsic dimensionality of the data in that space. The main drawback of this technique is the long computing time. The main contribution of the suggested work is to investigate the effect of fractal transform by adding R-tree index structure-based entropy to existing grid computing models to obtain a balanced infrastructure with minimal fault. In this regard, the presented work is going to extend the commonly scheduling algorithms that are built based on the physical grid structure to a reduced logical network. The objective of this logical network is to reduce the searching in the grid paths according to arrival time rate and path’s bandwidth with respect to load balance and fault tolerance, respectively. Furthermore, an optimization searching technique is utilized to enhance the grid performance by investigating the optimum number of nodes extracted from the logical grid. The experimental results indicated that the proposed model has better execution time, throughput, makespan, latency, load balancing, and success rate.

Multi-objective microservice deployment optimization via a knowledge-driven evolutionary algorithm

For the deployment and startup of microservice instances in different resource centres, we propose an optimization problem model based on the evolutionary multi-objective theory. The objective functions of the model consider the computation and storage resource utilization rate, load balancing rate, and actual microservice usage rate in resource service centres. The constraints of the model are the completeness of service, total amount of storage resources, and total number of microservices. In this study, a knowledge-driven evolutionary algorithm (named MGR-NSGA-III) is proposed to solve the problem model and seek the optimal deployment and startup strategy of microservice instances in different resource centres. The proposed model and solution have been evaluated via real data experiments. The results show that our approach is better than the traditional microservice instance deployment and startup strategy. The average computation rate, storage idle rate, and actual microservice idle rate were 13.21%, 5.2%, and 16.67% lower than those in NSGA-III, respectively. After 50, 100, and 150 evolutionary generations in serval operations, the population members in NGR-NSGA-III dominated the population members in NSGA-III 6,270, 3,581, and 7,978 times in average, respectively, which means that NGR-NSGA-III can converge to the optimal solution much quicker than NSGA-III.

A Reliable Friedman Hypothesis-Based Detection and Adaptive Load Balancing Scheme for Mitigating Reduction of Quality DDoS Attacks in Cloud Computing

The computing resource availability in a cloud computing environment is considered as the vital attribute among the security essentialities due to the consequence of on its on demand service. The class of adversaries related to the Distributed Denial of Service (DDoS) attack is prevalent in the cloud infrastructure for exploiting the vulnerabilities during the implementation of their attack that still make the process of providing security and availability at the same time as a challenging objective. In specific, The in cloud computing is the major threat during the process of balancing security and availability at the same time. In this paper, A Reliable Friedman Hypothesis-based Detection and Adaptive Load Balancing Scheme (RFALBS-RoQ-DDOS) is contributed for effective detection of RoQDDoS attacks through Friedman hypothesis testing. It also inherited an adaptive load balancing approach that prevents the degree of imbalance in the cloud environment. The simulation results of the proposed RFALBS-RoQ-DDoS technique confirmed a superior detection rate and a adaptive load balancing rate of nearly 23% and 28% predominant to the baseline DDoS mitigation schemes considered for investigation.

A novel four-tier architecture for delay aware scheduling and load balancing in fog environment

Fog computing paradigm is located between IoT devices and cloud paradigm that aim is to minimize the latency in terms of task scheduling and load balancing. To deal with the huge amount of data sensing from different IoT devices, in this paper we propose a four tiers architecture for delay aware scheduling and Load Balancing in the fog environment. Tier-1 is the bottom tier which consists of IoT devices. In the second tier, the applications (workloads) are categorized into two categories: High Priority (HP) and Low Priority (LP) by router based on the Dual Fuzzy Logic Algorithm. Fuzzifier considers four input metrics: task size, arrival time, minimum execution time and maximum completion time. A task with high priority is transmitted to the third tier (fog tier). In the third tier, a novel fog structure has been invoked namely Artificial Fractals consists of nodes. The fog nodes are clustered using K-means++ clustering algorithm. Each fog node is carried out several actions such as scheduling, monitoring, and communication. To schedule tasks within the fog node, we propose the Earliest Deadline First (EDF) task scheduling algorithm. The current usage of fog node is determined by Artificial Neural Network (ANN). If an IoT device does not get the required resource then the request is forwarded to the cloud tier. Our proposed work has been validated over a real-time VSOT (Video Surveillance/Object Tracking) application using iFogSim and the performance is evaluated in terms of response time, scheduling time, load balancing rate, delay, and energy consumption.

Map-optimize-reduce: CAN tree assisted FP-growth algorithm for clusters based FP mining on Hadoop

Over the past era, Frequent Pattern Mining (FPM) is emerging as a significant approach to discover fascinating knowledge concealed in the data. However, preceding works failed to address the validation of FPM with user queries and also achieving better scalability and execution time is still bottleneck owing to difficulties in handling large dataset. To address this downside, our proposed work establishes FPM using extend version of MapReduce framework in Hadoop environment. Our proposed work comprises of five processes that are: 1) Preprocessing 2) Affinity Propagation (AP) based Clustering 3) Load Balancing 4) Map-Optimize-Reduce 5) Mining User Queries. Primarily, our proposed work performs preprocessing to remove data redundancy. To speed up the MapReduce framework, we propose AP clustering which generates effective clusters from the given dataset. Load balancing is executed to balance load among different blocks concerning where reputation is computed. To avoid oversight in scanning and minimal searching space in MapReduce, optimizer is included between Mapper and Reducer where Emperor Penguin Colony (EPC) optimization is used. Frequent patterns are mined using CANonical order (CAN) tree based Frequent Pattern (FP) growth which reduces execution time and frequent tree construction. User provides Mining_Request to the Hadoop and frequent patterns are mined for given query which is send back to the user. If user given query is not present in the CAN tree, then it sends Relevance Feedback as a recommendation to the user. Finally, we validate our proposed work performance with the previous works for succeeding metrics that are Execution Time, Response Time, Load Balancing Rate, and Scalability.

Multi-objective computation offloading for Internet of Vehicles in cloud-edge computing

The Internet of Vehicles (IoV) has gained worldwide attentions as it provides the service of collecting real-time traffic information to improve the road safety. The IoV users can offload their computing tasks to the edge computing devices (ECDs) for low latency execution and the cloud can be engaged to process big data with sufficient computing resources. Though galactic convenience brought by the IoV cloud-edge computing system, it remains a challenge to manage the resource of ECDs by reducing the energy and time consumption while avoiding the situation of overload or underload of the ECDs to maintain the system-stability. Moreover, during the movement of the vehicles, the computing tasks and data may be uploaded to different ECDs and the data continuity may be destroyed. In this paper, a multi-objective computation offloading method (MOC) for IoV in cloud-edge computing is proposed to deal with the challenges above. A vehicle-to-vehicle communication-based route obtaining algorithm is designed first. Then, in order to ensure the trustworth of the IoV data, which ECD to upload the computing tasks to is selected. Under the case that all ECDs are overloaded, the computation offloading between ECDs and cloud is considered. In addition, non-dominated sorting genetic algorithm III is adopted to realize the multi-objective optimization of decreasing the load balancing rate and reduce the energy consumption in ECDs and shorten the time during processing the computing tasks. Furthermore, we employ the simple additive weighting and multiple criteria decision making to evaluate the solutions of our proposed method. Finally, experimental evaluations are conducted to validate the efficiency and effectiveness of our proposed method.