Load Balancing Model Research Articles

Mean Field and Refined Mean Field Approximations for Heterogeneous Systems

Mean field approximation is a powerful technique to study the performance of large stochastic systems represented as n interacting objects. Applications include load balancing models, epidemic spreading, cache replacement policies, or large-scale data centers. Mean field approximation is asymptotically exact for systems composed of n homogeneous objects under mild conditions. In this paper, we study what happens when objects are heterogeneous. This can represent servers with different speeds or contents with different popularities. We define an interaction model that allows obtaining asymptotic convergence results for stochastic systems with heterogeneous object behavior, and show that the error of the mean field approximation is of order $O(1/n)$. More importantly, we show how to adapt the refined mean field approximation, developed by Gast et al., and show that the error of this approximation is reduced to O(1/n^2). To illustrate the applicability of our result, we present two examples. The first addresses a list-based cache replacement model, RANDOM(m), which is an extension of the RANDOM policy. The second is a heterogeneous supermarket model. These examples show that the proposed approximations are computationally tractable and very accurate. They also show that for moderate system sizes (30) the refined mean field approximation tends to be more accurate than simulations for any reasonable simulation time.

Fast reactive flow simulations using analytical Jacobian and dynamic load balancing in OpenFOAM

Detailed chemistry-based computational fluid dynamics (CFD) simulations are computationally expensive due to the solution of the underlying chemical kinetics system of ordinary differential equations (ODEs). Here, we introduce a novel open-source library aiming at speeding up such reactive flow simulations using OpenFOAM, an open-source software for CFD. First, our dynamic load balancing model by Tekgül et al. [“DLBFoam: An open-source dynamic load balancing model for fast reacting flow simulations in OpenFOAM,” Comput. Phys. Commun. 267, 108073 (2021)] is utilized to mitigate the computational imbalance due to chemistry solution in multiprocessor reactive flow simulations. Then, the individual (cell-based) chemistry solutions are optimized by implementing an analytical Jacobian formulation using the open-source library pyJac, and by increasing the efficiency of the ODE solvers by utilizing the standard linear algebra package. We demonstrate the speed-up capabilities of this new library on various combustion problems. These test problems include a two-dimensional (2D) turbulent reacting shear layer and three-dimensional (3D) stratified combustion to highlight the favorable scaling aspects of the library on ignition and flame front initiation setups for dual-fuel combustion. Furthermore, two fundamental 3D demonstrations are provided on non-premixed and partially premixed flames, viz., the Engine Combustion Network Spray A and the Sandia flame D experimental configurations, which were previously considered unfeasible using OpenFOAM. The novel model offers up to two orders of magnitude speed-up for most of the investigated cases. The openly shared code along with the test case setups represent a radically new enabler for reactive flow simulations in the OpenFOAM framework.

Machine Learning-Based Load Balancing Algorithms in Future Heterogeneous Networks: A Survey

The massive growth of mobile users and the essential need for high communication service quality necessitate the deployment of ultra-dense heterogeneous networks (HetNets) consisting of macro, micro, pico and femto cells. Each cell type provides different cell coverage and distinct system capacity in HetNets. This leads to the pressing need to balance loads between cells, especially with the random distribution of users in numerous mobility directions. This paper provides a survey on the intelligent load balancing models that have been developed in HetNets, including those based on the machine learning (ML) technology. The survey provides a guideline and a roadmap for developing cost-effective, flexible and intelligent load balancing models in future HetNets. An overview of the generic problem of load balancing is also presented. The concept of load balancing is first introduced, and its purpose, functionality and evaluation criteria are then explained. Besides, a basic load balancing model and its operational procedure are described. A comprehensive literature review is then conducted, including techniques and solutions of addressing the load balancing problem. The key performance indicators (KPIs) used in the evaluation of load balancing models in HetNets are presented, along with the concurrent optimisation of coverage (CCO) and mobility robustness optimisation (MRO) relationship of load balancing. A comprehensive literature review of ML-driven load balancing solutions is specifically accomplished to show the historical development of load balancing models. Finally, the current challenges in implementing these models are explained as well as the future operational aspects of load balancing.

Optimal Load Balancing in Cloud Environment of Virtual Machines

Cloud resource scheduling is gaining prominence with the increasing trends of reliance on cloud infrastructure solutions. Numerous sets of cloud resource scheduling models were evident in the literature. Cloud resource scheduling refers to the distinct set of algorithms or programs the service providers engage to maintain the service level allocation for various resources over a virtual environment. The model proposed in this manuscript schedules resources of virtual machines under potential volatility aspects, which can be applied for any priority metric chosen by the server administrators. Also, the model can be flexible for any time frame-based analysis of the load factor. The model discussed in this manuscript relies on the Bollinger Bands tool for understanding the potential volatility aspects of a Virtual Machine. The experimental study of the model compared to the contemporary load balancing model called STLB (Starvation Threshold-based Load Balancing) refers to a simple and potential model that can be more pragmatic for sustainable ways of load balancing.

CHALLENGES OF USING THE FUZZY APPROACH IN EXASCALE COMPUTING SYSTEMS

In this paper were studied opportunities of using fuzzy sets theory for constructing an appropriate load balancing model in Exascale distributed systems. The occurrence of dynamic and interactive events in multicore computing systems leads to uncertainty. As the fuzzy logic-based solutions allow the management of uncertain environments, there are several approaches and useful challenges for the development of load balancing models in Exascale computing systems.

Research on load balancing of parallel component programs based on quantum particle swarm optimization algorithm

Parallel component applications are often deployed on heterogeneous clusters. Load balancing is very important for their performance requirement. Existing load balancing methods have high performance cost and poor balance effect. Based on the analysis of structures of parallel component applications, we established the mathematical model of load balancing for parallel components on heterogeneous clusters. We use the quantum particle swarm optimization algorithm to search the optimal solution of the proposed mathematical model and determine the best load balancing scheme. Comparing with the methods based on real-time detection and other swarm intelligence optimization algorithms, our method has lower balance cost, less number of iterations and better performance.

Machine learning‐based load distribution and balancing in heterogeneous database management systems

SummaryFor dynamic and continuous data analysis, conventional OLTP systems are slow in performance. Today's cutting‐edge high‐performance computing hardware, such as GPUs, has been used as accelerators for data analysis tasks, which traditionally leverage CPUs on classical database management systems (DBMS). When CPUs and GPUs are used together, the architectural heterogeneity, that is, leveraging hardware with different performance characteristics jointly, creates complex problems that need careful treatment for performance optimization. Load distribution and balancing are crucial problems for DBMSs working on heterogeneous architectures. In this work, focusing on a hybrid, CPU‐GPU database management system to process users' queries, we propose heuristical and machine‐learning‐based (ML‐based) load distribution and balancing models. In more detail, we employ multiple linear regression (MLR), random forest (RF), and Adaboost (Ada) models to dynamically decide the processing unit for each incoming query based on the response time predictions on both CPU and GPU. The ML‐based models outperformed the other algorithms, as well as the CPU and GPU‐only running modes with up to 27%, 29%, and 40%, respectively, in overall performance (response time) while answering intense real‐life working scenarios. Finally, we propose to use a hybrid load‐balancing model that would be more efficient than the models we tested in this work.

Implementation Model of Dynamic Load Balancing in Distributed System Based on Consistent Hash Algorithm

Implementation Model of Dynamic Load Balancing in Distributed System Based on Consistent Hash Algorithm

A Survey of Load Balancing and Implementation of Clustering-Based Approach for Clouds

Background: Generally, it is observed that there is not a single algorithm that classifies the task using Quality of Service (QoS) parameters requested by the task but instead focuses on classifying resources and balancing the task's using the availability of resources. In past literature, authors divided the load balancing solutions in three main parts workload estimation, decision making, task transferring. Workload estimation deals with identifying requirements for the incoming tasks on the system. Decision making is done to analyze that whether or not load balancing should be performed for the given node. If the decision for load balancing has been made then third step deals with transferring task to appropriate node to reach a saturation point where the system will be in the stable state. Objective: To address this issue, our approach is more focused upon on workload estimation and its main objective is to cluster the incoming heterogeneous task into generic groups. Another issue for this approach is that the client demand varies for the number of tasks. Thus, some attributes may be much more critical to a user then the others and this demand changes from user to user. Methods: This paper classify the tasks using QoS parameters and focused on work-load estimation. The main objective is to cluster the incoming heterogeneous task into generic groups. For this, KMedoid based clustering approach for cloud computing is devised and implemented. This approach is then compared with its different iterations to analyses the workload execution more deeply. Results: The analysis of our approach is computed using cloudsim simulator. Results and computations shows that the data is very uneven in initial times, as some clusters have only four elements and others are having much more elements. Whereas after the 20th iteration data observed is more normally balanced, so the clusters formed after 20th iteration were more stable than clusters formed initially i.e. 1st iteration. The number of iterations is also minimized to do unnecessary clustering as after a few steps the changes in medoids are very less. Conclusion: A brief survey of various load balancing techniques in cloud computing is discussed. These approaches are meta-heuristic in nature and have complex behavior and can be implemented in cloud computing. In our paper, K-Medoid based clustering approach for identifying the task into similar groups has also been implemented. Implementation is done on cloudsim simulation package provided by Cloud Labs, which is a java based open source package. The results obtained in our approach are limited to classification of tasks into various clusters. It would also useful where new task arrives and simply assign it to a VM that was created for some other element of that class. In future, this work can be expanded to create an effective clustering based model for load balancing.

On the Asymptotic Insensitivity of the Supermarket Model in Processor Sharing Systems

The supermarket model is a popular load balancing model where each incoming job is assigned to a server with the least number of jobs among d randomly selected servers. Several authors have shown that the large scale limit in case of processor sharing servers has a unique insensitive fixed point, which naturally leads to the belief that the queue length distribution in such a system is insensitive to the job size distribution as the number of servers tends to infinity. Simulation results that support this belief have also been reported. However, global attraction of the unique fixed point of the large scale limit was not proven except for exponential job sizes, which is needed to formally prove asymptotic insensitivity. The difficulty lies in the fact that with processor sharing servers, the limiting system is in general not monotone. In this paper we focus on the class of hyperexponential distributions of order $2$ and demonstrate that for this class of distributions global attraction of the unique fixed point can still be established using monotonicity by picking a suitable state space and partial order. This allows us to formally show that we have asymptotic insensitivity within this class of job size distributions. We further demonstrate that our result can be leveraged to prove asymptotic insensitivity within this class of distributions for other load balancing systems.

DLBFoam: An open-source dynamic load balancing model for fast reacting flow simulations in OpenFOAM

Computational load imbalance is a well-known performance issue in multiprocessor reacting flow simulations utilizing directly integrated chemical kinetics. We introduce an open-source dynamic load balancing model named DLBFoam to address this issue within OpenFOAM, an open-source C++ library for Computational Fluid Dynamics (CFD). Due to the commonly applied operator splitting practice in reactive flow solvers, chemistry can be treated as an independent stiff ordinary differential equation (ODE) system within each computational cell. As a result of the highly non-linear characteristics of chemical kinetics, a large variation in the convergence rates of the ODE integrator may occur, leading to a high load imbalance across multiprocessor configurations. However, the independent nature of chemistry ODE systems leads to a problem that can be parallelized easily (called an embarrassingly parallel problem in the literature) during the flow solution. The presented model takes advantage of this feature and balances the chemistry load across available resources. Additionally, a reference mapping model is utilized to further speed-up the simulations. When DLBFoam it utilized with both these features enabled, a speed-up by a factor of 10 is reported for reactive flow benchmark cases. To the best of our knowledge, this model is the first open-source implementation of chemistry load balancing in the literature. Program summaryProgram Title: DLBFoamCPC Library link to program files:https://doi.org/10.17632/bb9zjfzcmm.1Developer's repository link:https://github.com/blttkgl/DLBFoamLicensing provisions: GPLv3Programming language: C++Nature of problem: Solution of chemical kinetics in parallel reacting flow solvers raises a computational imbalance across multiprocessor architectures. DLBFoam balances the load distribution evenly, providing significant speed-up in reacting CFD applications.Solution method: The dynamic load balancing is implemented by distributing the point-wise chemistry problems from most loaded processes to less loaded ones using MPI communication protocol.Additional comments including restrictions and unusual features: The present model is designed to work with the standard chemistry model class available in OpenFOAM (versions 7 and 8). For the time being, the model does not support derived combustion models such as “TDAC” and covers gas-phase reaction kinetics only. In addition, the boundary surface chemistry problems are neglected by the model.

On the Asymptotic Insensitivity of the Supermarket Model in Processor Sharing Systems

The supermarket model is a popular load balancing model where each incoming job is assigned to a server with the least number of jobs among d randomly selected servers. Several authors have shown that the large scale limit in case of processor sharing servers has a unique insensitive fixed point, which naturally leads to the belief that the queue length distribution in such a system is insensitive to the job size distribution as the number of servers tends to infinity. Simulation results that support this belief have also been reported. However, global attraction of the unique fixed point of the large scale limit was not proven except for exponential job sizes, which is needed to formally prove asymptotic insensitivity. The difficulty lies in the fact that with processor sharing servers, the limiting system is in general not monotone. In this paper we focus on the class of hyperexponential distributions of order 2 and demonstrate that for this class of distributions global attraction of the unique fixed point can still be established using monotonicity by picking a suitable state space and partial order. This allows us to formally show that we have asymptotic insensitivity within this class of job size distributions. We further demonstrate that our result can be leveraged to prove asymptotic insensitivity within this class of distributions for other load balancing systems.

Directionally-Enhanced Binary Multi-Objective Particle Swarm Optimisation for Load Balancing in Software Defined Networks.

Various aspects of task execution load balancing of Internet of Things (IoTs) networks can be optimised using intelligent algorithms provided by software-defined networking (SDN). These load balancing aspects include makespan, energy consumption, and execution cost. While past studies have evaluated load balancing from one or two aspects, none has explored the possibility of simultaneously optimising all aspects, namely, reliability, energy, cost, and execution time. For the purposes of load balancing, implementing multi-objective optimisation (MOO) based on meta-heuristic searching algorithms requires assurances that the solution space will be thoroughly explored. Optimising load balancing provides not only decision makers with optimised solutions but a rich set of candidate solutions to choose from. Therefore, the purposes of this study were (1) to propose a joint mathematical formulation to solve load balancing challenges in cloud computing and (2) to propose two multi-objective particle swarm optimisation (MP) models; distance angle multi-objective particle swarm optimization (DAMP) and angle multi-objective particle swarm optimization (AMP). Unlike existing models that only use crowding distance as a criterion for solution selection, our MP models probabilistically combine both crowding distance and crowding angle. More specifically, we only selected solutions that had more than a 0.5 probability of higher crowding distance and higher angular distribution. In addition, binary variants of the approaches were generated based on transfer function, and they were denoted by binary DAMP (BDAMP) and binary AMP (BAMP). After using MOO mathematical functions to compare our models, BDAMP and BAMP, with state of the standard models, BMP, BDMP and BPSO, they were tested using the proposed load balancing model. Both tests proved that our DAMP and AMP models were far superior to the state of the art standard models, MP, crowding distance multi-objective particle swarm optimisation (DMP), and PSO. Therefore, this study enables the incorporation of meta-heuristic in the management layer of cloud networks.

RETRACTED ARTICLE: Cooperative Virtual Connectivity Control in Uplink Small Cell Network: Towards Optimal Resource Allocation

Nowadays, the application of soft computational techniques in power systems has been increasing with good acceptance under the machine learning umbrella. In this paper, first we presented a deep reinforcement learning approach to find the optimal configuration for HetNet systems. We used a huge quantity of radial configurations from a test system for training purposes. We also studied the joint carrier/power allocation problem in a multi-layer hierarchical networks to achieve the optimal power efficiency in addition to ensure the quality-of-experience for all subscribers. The proposed approach utilizes an adaptive Load Balancing model that aims to obtain “almost optimal” fairness among all servers from the key performance indicator viewpoints. Contrary to current model-based energy efficiency methods, we proposed a Joint Resource Allocation, Energy Efficiency and Flow Control algorithm to solve conventional non-convex and hierarchical optimization problems. Also, referred to SLA-based continuous resource allocation, we generalized the proposed algorithm to Joint Flow/Power Control, and Throughput Optimization algorithm to achieve the optimal energy efficiency beside of guaranteeing user throughput constraints. The simulation results exhibit that the proposed flow-controlled power optimization approach using the capability of network topology adjustment, is able to considerably enhance the energy efficiency compared to the conventional schemes.

Load balancing in cloud environs: Optimal task scheduling via hybrid algorithm

In cloud computing, a lot of challenges like the server failures, loss of confidentiality, improper workloads, etc. are still bounding the efficiency of cloud systems in real-world scenarios. For this reason, many research works are being performed to overcome the shortcoming of existing systems. Among them, load balancing seems to be the most critical issue that worsen the performance of the cloud sector, and hence there necessitates the optimal load balancing with optimal task scheduling. With the intention of accomplishing optimal load balancing by effectual task deployment, this paper plans to develop an advanced load balancing model with the assistance acquired from the metaheuristic algorithms. Usually, handling of tasks in cloud system is an NP-hard problem and moreover, nonpreemptive independent tasks are crucial in cloud computing. This paper goes with the introduction of a new optimal load balancing model by considering three major objectives: minimum makespan, priority, and load balancing, respectively. Moreover, a new single-objective function is also defined that incorporates all the three objectives mentioned above. Furthermore, the deployment of tasks must be optimal and for this a new hybrid optimization algorithm referred as Firefly Movement insisted WOA (FM-WOA) is introduced. This FM-WOA is the conceptual amalgamation of standard Whale Optimization Algorithm (WOA) and Firefly (FF) algorithm. Finally, the performances of the proposed FM-WOA model is compared over the conventional models with the intention of proving its efficiency in terms of makespan, task completion (priority), and degree of imbalance as well.

BiTE: a dynamic bi-level traffic engineering model for load balancing and energy efficiency in data center networks

With the recent significant growth of virtualization and cloud services, the data center network (DCN) as the underlying infrastructure is more important. The increasing and changing volume of workloads highlights critical issues such as load balancing and energy efficiency in data centers. Large path diversity in DCNs introduces multipath forwarding as a promising approach to improve load distribution. However, the over-provisioned DCNs consume large amounts of power while the network is under full capacity most of the time. Accordingly, this paper proposes BiTE, a dynamic bi-level traffic engineering (TE) scheme in a hierarchical Software Defined Networking (SDN)-based DCN to strike a balance between load balancing and energy efficiency objectives. BiTE consists of decision-making problems at two levels modeled as a multi-period bi-level optimization problem, where each decision maker optimizes one of objectives. According to the inherent complexity of bi-level programming, a co-evolutionary metaheuristic algorithm is proposed for solving BiTE. BiTE performance is evaluated in comparison to NSGA-II algorithm and four previously proposed TE schemes in terms of several load balancing and energy saving metrics under different scenarios. The results show that BiTE performs well in traffic load balancing while preserves the energy efficiency. We apply the Analytic Hierarchy Process (AHP) method to multi-criteria analyze and rank the performance of studied TE mechanisms. AHP results for different scenarios indicate that BiTE is in first or second place in terms of the overall performance score among six studied approaches.

Cost-Aware Ant Colony Optimization Based model for Load Balancing in Cloud Computing

: Balancing the incoming data traffic across the servers is termed as Load balancing. In cloud computing, Load balancing means distributing loads across the cloud infrastructure. The performance of cloud computing depends on the different factors which include balancing the loads at the data center which increase the server utilization. Proper utilization of resources is termed as server utilization. The power consumption decreases with an increase in server utilization which in turn reduces the carbon footprint of the virtual machines at the data center. In this paper, the cost-aware ant colony optimization based load balancing model is proposed to minimize the execution time, response time and cost in a dynamic environment. This model enables to balance the load across the virtual machines in the data center and evaluate the overall performance with various load balancing models. As an average, the proposed model reduces carbon footprint by 45% than existing methods.

Implementasi Algoritma Load Balancing PLBA Komputasi Grid pada Lab Environment Menggunakan PVM3

Load balancing is one of the main parts of scheduling Grid resources. One of the load balancing models on Grid resources is the hierarchical model. This model has the advantage that it requires minimal communication costs between one resource and another. The PLBA load balancing algorithm uses a hierarchical model with dynamically obtained threshold values, so that it can adjust conditions at a time, both the state of the resource, the state of the computer network, and the state of the recipient or client. PVM3 is a software system capable of optimizing heterogeneous resources, so that resources can work in parallel. Resources can also complete tasks well, even though they are very large and complex tasks. This research has implemented the PLBA load balancing algorithm, with the aim of optimizing Grid resources. This research has also developed the PLBA load balancing algorithm by changing the arguments for NPEList, so that resources can be grouped more optimally. The PLBA load balancing algorithm has been successfully developed by modifying the arguments for NPEList, so that the running time required to complete the given tasks is shorter, because resources can be grouped more optimally. This has been shown by the shorter average running time when using the modified NPEList argument (0.75 * threshold1 <= ALCi <= 1.25 * threshold1) is shorter, than using the NPEList argument in previous research (ALCi = threshold1). Comparison of the average running time has been obtained as follows : (82513.63740 : 67837.71720); (63869.92450 : 50722.17210); (858,96710 : 207,33680); (321.88000 : 126.89100); (768.54560 : 468.27190); (780.22770 : 279.43730).

Load balancing and neural dynamic model to optimize replicator dynamics controllers for vibration reduction of highway bridge structures

Earthquakes cause irreparable damages to the built environment, which has led bridge engineers to develop structural control systems to mitigate damage and improve vibration reduction in real-time. Among control systems, base isolation is one of the most commonly used passive control strategies for seismic protection of civil structures. Yet, it lacks real-time adaptability, has lower energy dissipation, and poor performance during near-fault earthquakes. To overcome these limitations, a hybrid control system comprised of semi-active magneto-rheological (MR) dampers and passive base isolation bearings is installed at the deck and piers for vibration reduction of highway bridge structures. This paper, inspired by evolutionary game theory and artificial intelligence, proposes data-driven replicator dynamic control algorithms to distribute the command voltage to the current driver of the semi-active MR dampers. It incorporates a load balancing strategy to reallocate additional resources. To achieve a high-performance design of the game-theory-inspired controllers, a patented neural dynamic model is used to optimize the control parameters. The evaluation of the proposed methodology uses a benchmark control problem based on the 91/5 highway bridge in Southern California subjected to near-field earthquake accelerograms. The performance of five different proposed controllers is compared with conventional Lyapunov and fuzzy logic control algorithms using 21 performance criteria. Results show the load balancing capability of the proposed control algorithms to mitigate the vibrations experienced by the bridge structure and further increase the durability of semi-active devices. The novelty of the methodology impacts how game-theory controllers make control decisions among multiple devices in engineering problems.

Self - Adaptive Load Balancing Using Live Migration of Virtual Machines in Cloud Environment

In this paper, a self-adaptive load balancing technique is proposed using live migration of heterogeneous virtual machines (VM) in a Hyper-V based cloud environment. A cloud supported plugin as a management activity within the infrastructure as a service strategy. It is proposed to assist the load balancing process in such a way so that all hypervisors are almost equally loaded once the overload status gets triggered. In the cloud computing environment, load balancing plays a major role if the large number of events triggered has a high impact on the performance of the system. The efficiency of cloud computing is based on the efficient load balancing having a self-adjustable technique using live migration of VMs across clusters of nodes. The proposed load balancing model is efficient in performance improvement by efficient resource utilization and also it helps to avoid the situation occurrence of server hanging by the cause of server overload within the infrastructure of multiple Microsoft Hyper-V hypervisors environment.