Load Balancing Algorithm Research Articles

The Techniques in Enhancing Bandwidth Load Balancing QoS at Local Area Network: A Review Paper

Bandwidth load balancing is a critical technique for improving the quality of service (QoS) in local area networks (LANs). Insufficient load balancing and QoS utilization can lead to network congestion, reduced performance, latency, packet loss, and an overall degradation of network performance. This paper presents an overview of load balancing techniques, load balancing algorithms, QoS parameters, load balancing strategies, and considerations for calculating bandwidth. The challenges of implementing load balancing algorithms and preferences for their implementation are discussed. Accurate network measurements and monitoring, coordination between network devices, security and privacy considerations, and careful evaluation of load balancing algorithms are among the challenges faced. The paper also discusses optimization and monitoring of bandwidth use, including options such as increasing bandwidth, bandwidth throttling, and data transfer throttling. The findings presented in this paper provide insights into the importance of load balancing and QoS in LANs and offer guidance for addressing related challenges.

Self-improved algorithm for cloud load balancing under SLA constraints

Self-improved algorithm for cloud load balancing under SLA constraints

Joint optimization of resource allocation and computation offloading based on game coalition in C-V2X

In order to solve the problem of limited resources in the vehicle, mobile edge computing (MEC) is integrated into the cellular-vehicle-to-everything (C-V2X) system to provide users with low-latency services. Considering the resource limitation of computing, storage and communication of MEC servers, it is necessary to improve the system performance through the collaborative optimization of multi-domain resources. Therefore, for applications with double dependence on time and data in C-V2X scenarios, we design a MEC hierarchical resource management framework to jointly optimize system offloading decision, scheduling decision, and caching decision to minimize the system delay. The optimization problem is decomposed into a resource allocation problem within a single MEC server and a load balancing problem among multiple MEC servers. For the former, we present a task scheduling algorithm based on the latest start time and a caching decision algorithm based on dynamic programming to minimize the average task completion delay; for the latter, we present a load balancing algorithm based on the coalition game to minimize the global system delay. Simulation results show that the proposed scheme can significantly improve the performance in terms of application completion delay, application failure rate and resource utilization compared with the benchmark schemes.

Artificial neural network based load balancing scheme for top of rack switches in optical data centers

Abstract Data centers serve as dedicated facilities for housing computer systems and their related components, including telecommunications and storage systems. They typically have high levels of security and environmental controls to ensure that the equipment housed within them functions optimally. Data center networks (DCNs) often employ load balancing algorithms to handle large volumes of traffic and ensure that all servers and switches are utilized equally, keeping the network running smoothly. However, as load on the server varies, therefore dynamic traffic management systems that can adjust traffic flow in real-time based on the current traffic state is required. This study presents an artificial neural network-based load balancing method. By training a feed-forward artificial neural network (ANN) using a back propagation (BP) learning algorithm, it evenly distributes workload over all of the nodes. Simulation results are also presented to prove the usefulness of the proposed load balancing mechanism. It is found that the load balancing scheme can reduce the packet blocking probability (PBP) by 10 folds and delay by about nearly 11 percent.

Joint RMSSA scheme and link load balancing for static SD-SCNs from model building to algorithm design

The spatial channel network (SCN) is a new optical network architecture that can support traffic requests from 100 Gb/s to 10 Tb/s and beyond. Software-defined networking (SDN) has superb management and control capabilities, making it easier to obtain network topology and link load information with it than with traditional networks. Combining the advantages of both, we propose a multi-plane SDN-based spatial channel network (SD-SCN) architecture and focus on solving the routing, modulation format, spatial lane, and spectrum block assignment (RMSSA) problem in static SD-SCNs. In this paper, we build a multi-plane network model of an SD-SCN, design the functional modules of each plane, and give the operation principle of the model. Furthermore, we formulate the RMSSA problem in the static SD-SCN model and propose a heuristic spatial lane and spectrum block minimization and load balancing (MLB2) algorithm to solve the problem. Also, we design an improved ant colony optimization (IACO) algorithm (the heuristic function and iteration criterion are optimized) to implement the routing path assignment function of the MLB2 algorithm. The simulation results show that the MLB2 algorithm can carry traffic requests with minimum network resources, and when the total traffic rate is high, the link load can be balanced by invoking the IACO algorithm to increase the network throughput. The MLB2 algorithm performs better in small-scale networks than in large-scale networks.

DetonationFoam: An open-source solver for simulation of gaseous detonation based on OpenFOAM

Detonation has promising applications in advanced propulsion systems, and numerical simulation is widely used to gain insights into the complex interaction between the hydrodynamic flow and chemical reactions involved in detonation. In this work, detonationFoam, an open-source solver for accurate and efficient simulation of compressible reactive flow and detonation are developed based on OpenFOAM. detonationFoam can simulate compressible, multi-component, reactive flow and it can accurately evaluate the detailed transport coefficients using the mixture-averaged transport model. Compared to rhoCentralFoam, the improved HLLC-P approximate Riemann solver is used in detonationFoam and it helps to accurately resolve shock waves appearing in detonation. Besides, the adaptive mesh refinement and dynamic load balancing algorithms are used in detonationFoam, which greatly improves the computational efficiency. Validation tests including homogenous ignition, unsteady diffusion, shock tube problem, premixed flame, planar detonation, double Mach reflection, detonation cellular structure and oblique detonation wave are conducted. These tests demonstrate that detonationFoam can be used to accurately and efficiently to simulate the compressible, multi-component reactive flow and detonation processes. Program summaryProgram Title: detonationFoamCPC Library link to program files:https://doi.org/10.17632/x45zh4nz28.1Developer's repository link:https://github.com/JieSun-pku/detonationFoamLicensing provisions: GPLv3Programming language: C++Nature of problem: Gaseous detonation involves different length scales and complicated chemistry. To accurately and efficiently simulate the gaseous detonation, adaptive mesh refinement needs to be conducted and detailed chemistry should be considered. Besides, the severe load imbalance caused by the chemical source term evaluation may greatly reduce the computation efficiency.Solution method: An open-source solver, detonationFoam is developed based on OpenFOAM. The species equations considering detailed chemistry are solved in detonationFoam and thereby detonation in a compressible, multi-component, reactive flow can be simulated. The adaptive mesh refinement technique and the dynamic load balancing algorithm are incorporated into detonationFoam. It is demonstrated that detonationFoam can accurately and efficiently simulate gaseous detonation.

A novel optimal management method for smart grids incorporating cloud-fog layer and honeybee mating optimization algorithm

As a result of cloud-fog (CF) technology, today's society is experiencing low delay, great performance, improved safety, and lower operating costs. As a result of integrating Smart Grid (SG) into the CF platform, the power supply is of higher quality, and the transmission, distribution, and production of power are secure; management of demand and supply is continuous. The study proposes integrating SG with CF-driven environments to improve source distribution. There are 6 fogs in various areas. Every fog connects to a cluster, and there are 500 smart houses in every cluster. Home energy demands are fulfilled by fogs using various load balancing algorithms (LBAs), which are implemented on Digital Twin Virtual Machines (DTDTVMs) and provided with a fast response time (RT) and processing time (PT). The study proposes a Honeybee Mating Optimization Algorithm to balance loads using improved service broker policies. After comparing the outcomes of the suggested LBA to the particle swarm optimization algorithm (PSO), it can be concluded the suggested LBA performs better in comparison with PSO. All the simulation results and comparisons have been performed on digital twin environment to provide more realistic framework for this study.

Server load estimation by Burr distribution mixture analysis of TCP SYN response time

Server load estimation is key in balancing traffic between servers when optimizing data center resources. Intrusive methods are sometimes difficult or impossible to implement. Therefore, non-intrusive estimation methods are the best alternative in these cases. The objective of this paper is to present a server load estimation method based on external network traffic measurements obtained in a vantage point close to the server. Statistical distributions of TCP SYN response time, that is, the time from SYN to SYN+ACK segments at the server side, are used to fit Burr Type XII heavy tail distribution mixtures. The fitting algorithm, based on maximum likelihood estimation, is developed in detail in this paper. Experimental data shows that the median of the fitted distribution correlates within the 95% confidence interval of the server load figures and, thus, it can be used as a non-intrusive and accurate method to measure it. This new method can be applied to almost any existing load balancing algorithm, as it does not make any assumption about the server, which is considered a black box.

A dynamic load balancing algorithm for CFD–DEM simulation with CPU–GPU heterogeneous computing

Computational fluid dynamics combined with discrete element method (CFD–DEM) is widely adopted to study particle–fluid multiphase systems. However, due to the global dynamical evolution and the naturally non-uniform distribution of particles, the computational load in parallel computing varies dynamically in each process, leading to significant load imbalance. Thus, a dynamic load balancing (DLB) algorithm is proposed for parallel CFD–DEM simulations in the CPU–GPU heterogeneous architecture. A type of computing load analyzing grid (AG) is developed which covers the entire simulation region. Then Kalman filtering and linear weighted method is used to solve the weight of fluid grids and particles. The domain decomposition scheme is updated according to the weights of AGs dynamically. This DLB method is tested for gas–solid fluidized beds and periodic gas–solid systems of different scales. Results show that the DLB algorithm can significantly speed up CFD–DEM simulation and the highest performance is 2.28 times faster with DLB.

STUDY OF HIGH AVAILABILITY AND PERFORMACE OFF SERVER CLUSTER

The article analyzes selected software solutions for balancing traffic in the server cluster: Traefik, HAProxy, and NGINX. For the demonstration, a system model consists of a cluster of three servers connected to the management servers with load-balancing solutions that share a public IP address. The application servers use the same database available in a multi-master configuration and the management servers are connected via the BGP protocol. User requests reach the server cluster through redundant traffic balancing subsystems. After testing the designed system, it was found that HAProxy is the best among all selected load-balancing solutions and ensures high cluster availability. While setting up the HAProxy it is recommended to choose the dynamic Least-Connections load balancing algorithm. Keywords: a server cluster, load-balancing, Round Robin, Least connections, HAPoxy

Distributed Multi-Agent Deep Q-Learning for Load Balancing User Association in Dense Networks

Distributed learning can lead to effective user association with low overhead, but faces significant challenges in incorporating load balancing at all base stations (BS) because of coupling constraints. In this paper, we propose a distributed multi-agent deep Q-learning model for user association to satisfy the load balancing constraint at every BS. In particular, we design a deep Q-network (DQN) with target Q-network and experience replay buffer at each user as an agent, and propose a multi-agent matching policy to control the number of users connected to each BS for load balancing. The policy enhances network throughput performance by implementing a novel updating rule for the preference list at each BS. The proposed multi-agent DQN model operates in a fully distributed manner where each agent only uses local information and requires no information exchange between agents. Simulation results demonstrate that our proposed algorithm outperforms a conventional distributed load balancing algorithm and approaches a centralized scheme performance, while exhibiting fast convergence and high adaptability to channel changes.

Dynamic Resource Allocation in Cloud Environments

Abstract: The provisioning and use of computing resources has been completely transformed by cloud computing, which provides previously unheard-of levels of scalability, flexibility, and cost-effectiveness. In order to maximize resource utilizatio and guarantee peak performance in cloud settings, dynamic resource allocation is essential. In order to provide a thorough grasp of the most recent developments in this subject, this survey paper offers an in-depth review of dynamic resource allocation methods in cloud computing. The survey includes a wide range of dynamic resource allocation techniques, including as cost-optimization methods, resource provisioning and scheduling techniques, and load-balancing algorithms. Each method is examined in terms of its advantages, drawbacks, and applicability to particular cloud deployment scenarios. The research also investigates evaluation approaches and performance indicators for evaluating the efficacy of dynamic resource allocation systems. It emphasizes the need for continued research and innovation to address the evolving demands of cloud computing environments.

CLOUD load balancing for storing the internet of things using deep load balancer with enhanced security

The traditional load balancing some disadvantages are (1) reduction in the wait times, (2) Storing encrypted data in a location is difficult. To solve this issues proposed work introduced a Deep Load Balancer (DLB) use of cloud load balancing for storing the Internet of Things (IoT). The work analyzed the drawbacks of traditional load balancing algorithms and proposes the use of DLB as an improved approach for balancing the load of IoT devices in a cloud environment. Proposed DLB strategy is the process of following steps are (i) normalizing and standardizing the attributes of the resources that are being managed. This step involves (ii) Allocating and optimizing constrained resources using a DLB. (iii) Succeeding in minimizing delay. The advantages of DLB for IoT storage are scalability, cost efficiency, and security is effectively discussed. Finally, DLB approach is which leverages the large amounts of data generated by IoT devices. Furthermore, a deep learning model is proposed for predicting the load balancing efficiency of DLB in a cloud environment. Finally, the experimental results are analyzed and the implications of the proposed approach are clearly discussed. The performance evaluation metrics are Response Time (RT), Makespan (MS), Associated Overhead (AO) and Migration Time (MT) of the proposed work DLB compared with existing techniques are TA, ESCE and TA + ESCE. The results demonstrated that DLB is a promising technique for cloud load balancing of IoT devices.

Comparative analysis of metaheuristic load balancing algorithms for efficient load balancing in cloud computing

Load balancing is a serious problem in cloud computing that makes it challenging to ensure the proper functioning of services contiguous to the Quality of Service, performance assessment, and compliance to the service contract as demanded from cloud service providers (CSP) to organizations. The primary objective of load balancing is to map workloads to use computing resources that significantly improve performance. Load balancing in cloud computing falls under the class of concerns defined as "NP-hard" issues due to vast solution space. Therefore it requires more time to predict the best possible solution. Few techniques can perhaps generate an ideal solution under a polynomial period to fix these issues. In previous research, Metaheuristic based strategies have been confirmed to accomplish accurate solutions under a decent period for those kinds of issues. This paper provides a comparative analysis of various metaheuristic load balancing algorithms for cloud computing based on performance factors i.e., Makespan time, degree of imbalance, response time, data center processing time, flow time, and resource utilization. The simulation results show the performance of various Meta-heuristic Load balancing methods, based on performance factors. The Particle swarm optimization method performs better in improving makespan, flow time, throughput time, response time, and degree of imbalance.

A Novel Heterogenous Dominant Sequence Clustering for Task Scheduling and Optimal Load Balancing Using JSO in Cloud

Cloud computing (CC) is rapidly increasing and being used more and more in information technology (IT) contexts. Among the hottest issues in the world of CC is task scheduling. In cloud datacentres, load balancing is accomplished using a variety of scheduling techniques, although lengthening the parallel time. By taking task duration and VM capacity into account, this study proposes a cluster-based task scheduling paradigm. The makespan and execution duration should be reduced, the suggested system engages in dynamic load balancing. In this study, we suggest a unique method called HDDSC-JSO, which employs the Jellyfish Swarm Optimization (JSO) algorithm for load balancing and heterogeneous Density based dominant sequence clustering (HDDSC) for job scheduling. Using the HDSC technique, It presents a graph of one or more groups representing user tasks, the tasks of users are first clustered. The Adapted Diverse Expeditious Termination Time (ADETT) method is used to score each work after task clustering. whenever the job with the greatest priority is scheduled first. Next, using a JSO algorithm, load balancing is carried out, distributing the load according to the weight and capacity of the server as well as the connection of the client to the server. Task allocation chooses a heavily weighted or unconnected server, lengthening the response time. Finally, measures including response time, makespan, resource consumption, and service dependability were used to assess the suggested architecture.

A Novel Approach to Load Balancing and Security using SSL in Cloud Computing Environment

Cloud computing has become an integral part of modern-day computing due to its numerous benefits, such as scalability, availability, and cost-effectiveness. However, load balancing and security remain significant challenges in cloud computing environments. In this paper, we propose a novel approach to load balancing and security using SSL in cloud computing environments. We designed a system architecture that consists of a load balancer, multiple servers, and SSL certificates. We developed a load balancing algorithm that considers the current workload of each server and the incoming traffic to distribute traffic among servers based on their current workload and available resources. We implemented SSL encryption to secure communication between the client and server, ensuring data confidentiality. We also implemented several security measures to prevent unauthorized access to the system and detect and prevent attacks on the system. Our performance evaluations demonstrate that our approach outperforms traditional load balancing and security approaches. Our approach provides a robust and secure system architecture that ensures optimal performance and data confidentiality in cloud computing environments.

In Improved Algorithm for Load Balancing techniques Over Cloud Computing

The term "cloud computing" describes the services and programmes that data centres make available to users all over the world. Online access is provided for all services and programmes. Virtualization is a crucial component of the cloud computing environment, and virtual machine migration is one of its key components. Virtual machine migration is the process of moving an operational virtual machine to a destination computer where it continues to function normally with all of its installed programmes and operating system. Making server balancing easier. By dispersing the workload among available servers, this boosts performance. There are several load balancing algorithms, which may be divided into static and dynamic load balancing methods.

Reinforcement learning for communication load balancing: approaches and challenges

The amount of cellular communication network traffic has increased dramatically in recent years, and this increase has led to a demand for enhanced network performance. Communication load balancing aims to balance the load across available network resources and thus improve the quality of service for network users. Most existing load balancing algorithms are manually designed and tuned rule-based methods where near-optimality is almost impossible to achieve. Furthermore, rule-based methods are difficult to adapt to quickly changing traffic patterns in real-world environments. Reinforcement learning (RL) algorithms, especially deep reinforcement learning algorithms, have achieved impressive successes in many application domains and offer the potential of good adaptabiity to dynamic changes in network load patterns. This survey presents a systematic overview of RL-based communication load-balancing methods and discusses related challenges and opportunities. We first provide an introduction to the load balancing problem and to RL from fundamental concepts to advanced models. Then, we review RL approaches that address emerging communication load balancing issues important to next generation networks, including 5G and beyond. Finally, we highlight important challenges, open issues, and future research directions for applying RL for communication load balancing.

DYNAMIC LOAD BALANCING FOR CLOUD: A REVIEW

The newest internet-based technology that places a strong emphasis on business computing is called cloud computing. Load balancing aids in enhancing the centralized server's efficiency. Using an analytical tool called cloud analyst, numerous algorithms are analyzed in the current work. Load balancing algorithms are also compared. The cloud computing load balancing issue is a significant one, a crucial element for proper system performance, and it has the potential to slow the industry's rapid growth. Recently, there has been a fast increase in the number of customers from all over the world requesting various services.

Controller Location and Load Balancing Integrated Solution

The usage of multi-controller SDNs is currently the most efficient approach for constructing the core of communication networks of the fifth and following generations. One of the top priorities in the study of this topic is occupied by the optimisation of the network core construction since it involves relatively high expenses when developing communication networks of the fifth and future generations. Due to the complexity of the problems being tackled, there are currently a number of load balancing algorithms and algorithms for arranging controllers in multicontroller networks that are based on meta-heuristic methods. These algorithms allow for the optimum possible utilisation of controller resources in such networks. However, a comprehensive solution to the load balancing and controller placement issues has yet to be discovered. The answer to such an issue is the focus of this article. The report suggests using network clustering in conjunction with the meta-heuristic chaotic salp swarm technique, which has shown to be effective in prior research on the challenges of creating multi-controller networks, to accomplish this goal. The salp swarm algorithm in the paper is adjusted to take into account the integral solution to the problem of deploying controllers based on clustering of a multi-controller network and load balancing. By contrasting the simulation results with those from the well-known meta-heuristic particle swarm algorithms optimization and the grey wolf GWO, as well as the previous version of the chaotic salp swarm algorithm CSSA, the effectiveness of the proposed solution was evaluated.