Load Balancing Method Research Articles

Feedback Learning in Software-Defined Mobile Network for Resource Aware Load Balancing Under Fault Tolerance Conditions

Fault-tolerant-based load balance resource allocation can help in the explosive data flow in the mobile network. System parameter function, system load factors, network-level configuration, network characteristics, and routing parameters are all affected by volatile data. In today's era of Big Data, one of the most important areas of study in mobile communications is how to adapt to traffic flow. The accessibility of load balancing sensors helps eliminate delays, which in turn helps reduce energy consumption and shorten execution time. In this research, we present a load balancing method for software-defined mobile networks (SDMNs) that is known to maximize the utility of the sensors by considering both the processing power of the sensors and the requirements of their sources. A proactive action technique that takes advantage of the wireless facility is proposed, and a wireless load balancing design solution using the learning method is then utilized in the designed framework. To achieve high resource utilization, we use a method based on convergence. Intelligent resource utilization by multiple sensor devices can help to cope with high bandwidth applications such as multimedia in mobile networks. Compared to conventional methods, the model has the potential to achieve better results.

An Optimal Virtual Machine Placement Method in Cloud Computing Environment

Cloud computing is formally known as an Internet-centered computing technique used for computing purposes in the cloud network. It must compute on a system where an application may simultaneously run on many connected computers. Cloud computing uses computing resources to achieve the efficiency of data centres using the virtualization concept in the cloud. The load balancers consistently allocate the workloads to all the virtual machines in the cloud to avoid an overload situation. The virtualization process implements the instances from the physical state machines to fully utilize servers. Then the dynamic data centres encompass a stochastic modelling approach for resource optimization for high performance in a cloud computing environment. This paper defines the virtualization process for obtaining energy productivity in cloud data centres. The algorithm proposed involves a stochastic modelling approach in cloud data centres for resource optimization. The load balancing method is applied in the cloud data centres to obtain the appropriate efficiency.

SAAQ: A Characterization Method for Distributed Servers in Ubicomp Environments.

The increasing evolution of computing technologies has fostered the new intelligent concept of Ubiquitous computing (Ubicomp). Ubicomp environments encompass the introduction of new paradigms, such as Internet of Things (IoT), Mobile computing, and Wearable computing, into communication networks, which demands more efficient strategies to deliver tasks and services, considering heterogeneity, scalability, reliability, and efficient energy consumption of the connected devices. Middlewares have a crucial role to deal with all these aspects, by implementing efficient load balancing methods based on the hardware characterization and the computational cost of the queries and tasks. However, most existing solutions do not take into account both considerations in conjunction. In this context, we propose a methodology to characterize distributed servers, services, and network delays in Ubicomp environments, based on the Server Ability to Answer a Query (SAAQ). To evaluate our SAAQ-based methodology, we implemented a simple middleware in a museum context, in which different IoT devices (e.g., social robots, mobile devices) and distributed servers with different capabilities can participate, and performed a set of experiments in scenarios with diverse hardware and software characteristics. Results show that the middleware is able to distribute queries to servers with adequate capacity, freeing from service requests to devices with hardware restrictions; thus, our SAAQ-based middleware has a good performance regarding throughput (22.52 ms for web queries), end-to-end delay communications (up to 193.30 ms between San Francisco and Amsterdam), and good management of computing resources (up to 80% of CPU consumption).

An Enhanced Load Balancing Technique for Big-data Cloud Computing Environments

The need for cloud computing load balancing is a peculiar area of interest for researchers because it affects both the quality of service provided to users and resource utilisation on the part of cloud service providers. Due to the requirement to minimise processing costs, enhance throughput, improve resource efficiency, and optimise cloud node arrangement, existing cloud computing load balancing methods have been found to be restricted in their capacity to manage big-data cloud system load distribution. This research developed a novel Central-Regional Architecture Based Load Balancing Technique (CRLBT) different from the known central, distributive, and hierarchical cloud architectures. The proposed technique was developed by combining a formulated throughput maximisation algorithm with the algorithms; Throughput Maximised-Particle Swarm Optimisation (TM-PSO) and Throughput Maximised-Firefly optimisation (TM-Firefly). The developed technique was implemented using the MATLAB R2018 software package. The performance of the CRLBT in comparison to the already-in-use PSO and Firefly algorithms was evaluated using response time, throughput, job rejection ratio, and CPU utilisation rate. The significance of the improvement in load balancing brought about by the new approach was further assessed using a statistical T-Test. The results showed that the proposed CRLBT significantly outperformed the PSO and Firefly techniques regarding response time, throughput CPU utilisation rate, and task rejection ratio. Finally, significant improvements in response time, tax rejection ratio, CPU utilisation rate, and network throughput proved the ability of the proposed technique to handle task-resource distribution of big-data cloud centres superiorly.

Challenges of Load Balancing Techniques in Cloud Environment: A Review

To highlight issues and challenges of the Load Balancing Algorithm (LBA) in the context of cloud computing. The authors of this work discussed load balancing and the load balancing problems in cloud computing, how to solve them, the basic techniques used to maintain load over the cloud, and the benefits and drawbacks of these algorithms. Furthermore, the static and dynamic load balancing strategies are compared. Load balancing methods in the cloud for data centers must avoid VM overload/low load, which is a challenge in cloud computing. Load balancing mechanisms aid in the management of workloads. The primary goal of load balancing among machines is to spread workloads and computing resources across one or more servers while lowering energy consumption and maximizing resource usage. Cloud computing is a type of computing in which scalable resources are made available on-demand and are frequently virtual, as in an online service. For a variety of reasons, including cost saving, speed, efficiency, performance, and security, cloud computing has recently become a popular choice for individuals and enterprises. Cloud computing uses the Internet to deliver a variety of services to a company's computers and devices. These resources can include data storage, databases, servers, networks, and software, among other tools and applications. In this paper, developers and researchers must design and construct a load balancer e for parallel and distributed cloud systems.

HIPA: A hybrid load balancing method in SSDs for improved parallelism performance

NAND Flash-based SSDs have been widely adopted as underlying storage devices in storage systems thanks to high random performance in the SSDs. Because of inherent rich parallelism resources (channel, chip, plane, and die) inside an SSD, many researchers pay much attention on parallelism improvement. Page allocation policies (static and dynamic page allocation) in an SSD aim to translate logical addresses of I/O requests on the host into physical addresses in flash memory space. Existing static page allocation policies suffer from severe load unbalance inside SSDs. Dynamic allocation policies employed in high-performance SSDs address the load balancing issue. However, dynamic allocation-based I/O requests flow into fewer parallelism resources, deteriorating read I/O-requests parallelism. Recognizing that SSD performance can be optimized by reducing read parallelism loss, we propose a hybrid page allocation strategy named HIPA to fully exploit the advantages of dynamic and static allocation to achieve read/write parallelisms inside an SSD. HIPA embraces a load prediction mechanism to monitor die-level load in real-time, thereby determining a page allocation policy based on the status of die-level load. A static page allocation policy is triggered in case of balanced die-level load. When performance degrades due to imbalance in die-level load, HIPA dynamically changes the gear to a dynamic allocation policy, aiming to balance the load on dies. Thus, HIPA achieves the maximum read parallelism rather than crumbling write performance. Conducting the extensive experiments, we validate the advantages of HIPA in terms of average response time, plane-level write, and erase standard deviation. The findings unveil that compared with the four popular page allocation policies (CWDP, CHIP-D, DIE-D, and PLANE-D), HIPA slashes the average response time by up to 58% with an average of 20% and 81% with an average of 33% compared with the dynamic allocation (DIE-D) with the lowest response time and the static strategy, respectively; (2) drives up the write standard deviation degree of the static strategy by up to 44%; (3) improves erase standard deviation rate by up to 43%.

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Task scheduling and load balancing problem of heterogeneous computing environment (HCE) is getting more and more attention these days and has become a research hotspot in this field. The task scheduling and load balancing problem of heterogeneous environment, which refers to assigning a set of tasks to a specific set of machines with different hardware and different computing performance with the goal of minimizing task processing time and keeping load balance among machines, has been proved to be an NP-complete problem. The development of artificial intelligence provides new ideas to solve this problem. In this paper, we propose a novel task scheduling and load balancing method based on optimized deep reinforcement learning in HCE. First, we formulate task scheduling problem as a Markov decision process and then adopt a dueling double deep Q-learning network to search the optimal task allocation solution. Then we use two well-known large-scale cluster data sets Google Cloud Jobs data set and Alibaba Cluster Trace data set to validate our approach. The experimental results show that compared with other existing solutions, our proposed method can achieve much shorter task response time and better load balancing effect.

Implementasi Metode Load Balancing Sebagai Upaya Meningkatkan Kinerja Server

The use of the internet turns out to cause problems that must be found a solution. One of them is the service provider's server load which continues to increase. This condition is triggered by the increasing number of clients from time to time. Some sites even reported receiving hundreds of thousands of connection requests simultaneously from a number of clients. From these problems, research is needed that focuses on how to design and build a server system that is able to handle the increase in incoming requests so that the server load can be unraveled. The purpose of this research is that the service provider's server can improve its service to the client. There are several approaches to overcome these problems, one of which is by applying the load balancing method. So that by implementing load balancing, the incoming large load will be distributed to each of the service provider's servers. In the tests that have been carried out, the scalability of the system has increased. This is proven when a system with load balancing is given 10000 connections, the test results have an average response time of 44.42 ms. As for the system without load balancing, the test results have an average response time value of 185.88 ms. From the test results, it can be seen that the average response time of the server system with load balancing is smaller than without load balancing, so the service performance of the system can be continuously improved by implementing load balancing.

Energy-Aware VM Scheduler

Cost is the backbone of any business model to sustain and growth in the competitive business market. Considering this, higher energy consumption may affect the operational cost of any industry. Cloud computing is one of the most popular IT business model for service provider and its users. It is observed in many research, that the average cost of the services are highly dependent upon the run time and power consumption. More power consumption effect the environmental things as well. In this review, more than 100 research articles are considered to evaluate the energy consumption methods, issues and challenges from 2009 to 2021. Based on the study, the energy-aware load balancing methods are classified into four major clusters. The most cited methods are compared based on method used, platform where it is deployed, different evaluation parameters like cost, run time, Virtual Machine utilization, Service-level-agreement violation rate, and Quality-of-service QoS. The result of this review is presented as open research issues and challenges for forthcoming research.

Research on Detection and Early Warning Mechanism of Emergency Public Health Medical Education System Based on Internet of Things Technology.

Sudden public health and medical education events have tested the stability of society to a great extent. The government need to strengthen capacity building, make use of system dynamic supervision, warn public health events in advance, and minimize the impact scope and related harmfulness of events. This not only facilitates the rapid mobilization of resources by the later government but also facilitates the comprehensive and detailed deployment and arrangement of decision-makers. As we all know, the Internet of Things is used by all walks of life because of its outstanding advantages of low power consumption, low cost, and wide range. Therefore, this article takes the Internet of Things as the technical basis of the system. According to the actual demand and resource design, it includes two system functions: detection and early warning. The results show that: (1) considering the practical principle, the evaluation system interface found that the scores of font size and color style are all below 80%, which need to be optimized and adjusted; the overall interface basically meets the needs of users. (2) The throughput of the three methods is different. The CoAP-E has superior throughput. (3) With the increase in packet loss rate, the request success rate of the CoAP method decreases in a “drop” manner. The CoAP-E method in this article has the best performance. (4) When the packet loss rate is 25%, the network adaptability of this method is the strongest, and the retransmission rate is less than 18%; the CoAP method is as high as 35%. (5) When the number of concurrent requests is less than 2500, there is no obvious difference between the three methods; the optimal performance of the dynamic load balancing method is 10.1 s. (6) The system comprehensively considers various factors of five site selections. The highest comprehensive score of Final Site, 5 is 8.7, which can be used as the resettlement place of emergency rescue facilities. This article starts from the characteristics and needs of public emergencies, and the final set of the system runs well. It can quickly reflect public health emergencies and medical education events. Use the most effective system functions for risk control, and maximize the analysis, organization, and coordination of events. The follow-up optimization of system details needs to be studied.

Design of Load Balancing Using Static Route Address List Method In The Case Study of Tambakrejo Village Tulungagung

internet plays a very important role today, both to search for information and knowledge. In the development of internet networks, many factors influence it, such as the geographical location of the area, supporting facilities such as signal towers, construction costs, and Internet Service Providers (ISP) that cover the area. The purpose of this study is to build an internet network in Tambakrejo village, which has very difficult internet access due to its geographical location which is very far from urban areas and very few supporting facilities in the construction of internet networks, so the authors develop a solution using devices such as the Router Router, hubs, dongle modems, and bolic e-goen pans, and uses a load balancing method to stabilize the activity load of all connected devices. the final result expected by the authors in this study is so that people who live in the Tambakrejo village of Tulungagung city can feel internet access that is easier and more stable, and the construction of their internet network does not cost much.

SFC Provisioning With Load Balancing Method in Multi-Tier Fog Networks

Network function virtualization (NFV) requires service function chain (SFC) provisioning on cloud or fog servers. Now fog nodes offers short provisioning times as compared to the cloud, albeit limited resources. This makes fog nodes vulnerable to saturation if users demand computation-intensive services, where offloading to the cloud is prohibited due to the prolonged delays. Hence, this letter proposes a novel SFC provisioning scheme for fog paradigms that achieves load balancing (LB) and redistribution between heavily- and lightly-loaded nodes, without exceeding delay bounds. The scheme features high admission rates and reduced delays versus prominent solutions such as standalone delay or load minimization methods.

GOP-SDN: an enhanced load balancing method based on genetic and optimized particle swarm optimization algorithm in distributed SDNs

GOP-SDN: an enhanced load balancing method based on genetic and optimized particle swarm optimization algorithm in distributed SDNs

Load Balancing and Parallel Computation Model for Performance and Accuracy over the Cluster of Nodes

Cloud computing can be online based network engineering which contributed with a rapid advancement at the progress of communication technological innovation by supplying assistance to clients of assorted conditions with aid from online computing sources. It's terms of hardware and software apps together side software growth testing and platforms applications because tools. Large-scale heterogeneous distributed computing surroundings give the assurance of usage of a huge quantity of computing tools in a comparatively low price. As a way to lessen the software development and setup onto such complicated surroundings, high speed parallel programming languages exist which have to be encouraged by complex operating techniques. There are numerous advantages for consumers in terms of cost and flexibility that come with Cloud computing anticipated uptake. Building on well-established research in Internet solutions, networks and utility computing, virtualization et cetera Service-Oriented Architectures and the Internet of Services (IoS) have implications for a wide range of technological issues such as parallel computing and load balancing as well as high availability and scalability. Effective load balancing methods are essential to solving these issues. Adaptive task load model is the name of the method we suggest in our article for balancing the workload (ATLM). We developed an adaptive parallel distributed computing paradigm as a result of this (ADPM). While still maintaining the model's integrity, ADPM employs a more flexible synchronization approach to cut down on the amount of time synchronous operations use. As well as the ATLM load balancing technique, which solves the straggler issue caused by the performance disparity between nodes, ADPM also applies it to ensure model correctness. The results indicate that combining ADPM and ATLM improves training efficiency without compromising model correctness.

Towards Investigation of Various Load Balancing Techniques in Cloud Computing

Cloud computing is an on-demand service where customers may access any time common IT resources, information, software and other equipment. It is a web-based development that offers virtual resources over the Internet as a service. The higher the cloud use, the higher the charge. The allocation of loads to components processing is a challenging phenomenon.In a multi-node system, there is a very good possibility that some nodes will be idle while others will be overloaded. The load balancing algorithms' objective is to keep the load on each processing element constant. A technique for Random Load Balancing in Cloud Computing is devised, in which the amount of user requests is instantly assigned to the resources. This method employs a random strategy to decrease the request's waiting time. This proposed load balancing technique is simulated in Cloud Analyst tool. The performance comparison study between proposed random method and other available load balancing methods is conducted. It is found that the performance of proposed random method is better in terms of response time.Keywords: Cloud Computing, Load Balancing, Response Time, Virtual Machine, Sorting

LOAD BALANCING-FAILOVER METHODS USING STATIC ROUTE WITH ADDRESS LIST, ECMP, PCC, AND NTH FOR OPTIMIZING LAN NETWORK : A COMPARISON

Internet network is a means of infrastructure to support the learning and working process. Some internet network problems that often occur are internet connection is lost, the connection is slow, and the output does not match the bandwidth that is owned. This can be accommodated by using 2 (two) internet modem units from different ISP combined with the Load Balancing process. Load Balancing used to combine two internet modems so that one connection can become a backup connection if the main connection is lost. Nowadays Load Balancing has 4 (four) methods, they are Static Router with Address List, ECMP, PCC, and Nth. The problem is choosing the best method for Load Balancing. This research uses the PPDIOO network development method. From the results of tests conducted in this research indicate the balance of internet access and bandwidth performance owned by ISP1 and ISP2 after the Load Balancing process is carried out. From testing 4 (four) Load Balancing methods, the results show that the Nth method produces 79.2% bandwidth by testing for 40 (forty) days. The conclusion is that the Nth method is more effective to be applied on a LAN network compared to other Load Balancing methods because it can divide the internet connection path when browsing, downloading, and can do a failover. Expectations going forward after applying Load Balancing Nth method can improve internet performance that is used every day for learning and working activities in an organization. Keywords: Load Balancing, Failover, Static Route with Address List, ECMP, PCC, Nth.

Research on Load Balancing and Caching Strategy for Central Network

The central network architecture takes the information content as the processing object and can better meet the user access needs. However, the traditional network node load balancing and caching strategy has been difficult to adapt to the development of the central network architecture. Therefore, this article proposed a load balancing and cache management strategy based on the central network in order to provide a reference for the architecture and application of the central network. Based on the analysis of the existing network architecture, this article expounded the networking form and characteristics of the central network system. By analyzing the load scheduling requirements of network nodes, combined with the transmission characteristics of resource requests in the central network, a cache node load balancing method suitable for the requirements of the central network was proposed based on the existing load balancing algorithms. In addition, by analyzing the cache management strategy and its impact on the performance of the network system, a cache node information forwarding model with resource requests as the object in the central network environment was given. Finally, through experimental test and comparative analysis, the results showed that the method proposed in this article had certain feasibility and effectiveness. Compared with other typical strategies, the load balancing and caching strategy proposed in this article can better meet the user needs of the central network.

A Reinforcement Learning-Empowered Feedback Control System for Industrial Internet of Things

The rapid development of the Industrial Internet of Things (IIoT) enables IIoT devices to offload their computation-intensive tasks to nearby edges via wireless base stations and thus relieve their resource constraints. To better guarantee quality-of-service, it has become necessary to cooperate multiple edges instead of letting them work alone. However, the existing solutions commonly use a centralized decision-making manner and cannot effectively achieve good load balancing among massive edges that are widely distributed in IIoT environments. This results in long decision-making time and high communication costs. To address this important problem, in this article, we propose a reinforcement learning (RL)-empowered feedback control method for cooperative load balancing (RF-CLB). First, by integrating RL and machine learning (ML) algorithms, each edge independently schedules tasks and performs load balancing between adjacent edges based on the local information. Next, through feedback control and multiedge cooperation, the objective multiedge load-balancing plan for IIoT can be found. Simulation results demonstrate that the RF-CLB chooses the adjustment operations of load balancing with 96.3% correctness. Moreover, the RF-CLB achieves the near-optimal performance, which outperforms the classic ML-based and rule-based methods by 6–9% and 10–12%, respectively.

Generative Adversarial Network for Simulation of Load Balancing Optimization in Mobile Networks

<p>The commercial operation of 5G networks is almost ready to be launched, but problems related to wireless environment, load balancing for example, remain. Many load balancing methods have been proposed, but they were implemented in simulation environments that greatly differ from 5G networks. Current load balancing algorithms, on the other hand, focus on the selection of appropriate Wi-Fi or macro & small cells for Device to Device (D2D) communications, but Wi-Fi facilities and small cells are not available all the time. For this reason, we propose to use the macro cells that provide large coverage to achieve load balancing. By combing Generative Adversarial Network (GAN) with the ns-3 network simulator, this paper uses neural networks in TensorFlow to optimize load balancing of mobile networks, increase the data throughput and reduce the packet loss rate. In addition, to discuss the load balancing problem, we take the data produced by the ns-3 network simulator as the real data for GAN.</p> <p> </p>

Dynamic load balancing with over decomposition in plasma plume simulations

An electric propulsion plasma plume simulation employs the Particle-in-Cell (PIC) model for heavy species (i.e. ions and neutral atoms) and yields a highly non-uniform particle distribution at steady state. For parallel simulations, partitioning the computational domain uniformly and evenly assigning the subdomains to MPI processes would never lead to properly balanced loads across MPI processes. For this reason, a patch-based dynamic load balancing method with over-decomposition and Hilbert space-filling curve has been implemented into the Thermophysics Universal Research Framework (TURF). The data transfer is accomplished by utilizing TURF's serialization and deserialization feature, in which the tree hierarchical object structure is copied into a contiguous memory block of data, and the tree hierarchy is reconstructed after the data transfer. This generalized dynamic load balancing approach allows for the same routine to be used for any models besides the PIC model in TURF (e.g. fluid, continuum kinetic, hybrid models, etc). This paper first introduces individual pieces of TURF that enable dynamic load balancing when they are combined. Then, the dynamic load balancing method is demonstrated in three different particle simulations, showing performance gains when the number of subdomains is larger than that of MPI processes. The benefit is even more notable in simulations with highly non-uniform particle distributions at steady state, commonly seen in plasma plume simulations.