Load Balancing

Although the use of electronic component placement machines has brought reliability and speed to the printed circuit board (PCB) assembly process, to get higher utilization, one needs to solve the resulting complex operations research problems efficiently. In this study, the problem of distributing the assembly workload to two machines deployed on an assembly line with two identical component placement machines to minimize the line idle time is considered. This problem is NP-Complete even in its simplest form. A mathematical model and several heuristics have been proposed to solve this problem efficiently.

Since the last decade, Internet users increased rapidly and most of them are depending on the World Wide Web (WWW) service for achieving daily routine. Having Internet access and especially WWW sometimes users face difficulties because of various security problems. The most dangerous and serious threats that make Internet services impossible is Denial of Service (DoS) and its severe type ‘Distributed Denial of Service (DDoS)’. In this paper, the performance of different web servers in Network Load Balancing (NLB), cluster-based and none clustered are analyzed. Furthermore, we evaluate the impact of TCP SYN flood attack with massive concurrent HTTP load traffic on web server’s average response time, throughput and average CPU usage. The results show that Internet Information Service 10.0 (IIS10.0) on Windows server 2016 is more vulnerable to attacks compared to Apache2 on Ubuntu 16.04. The results also show that the IIS10.0 NLB clustered web servers is the most suitable mechanism for...

One of the today issues in software engineering is to find new effective ways to deal intelligently with the increasing complexity of distributed computing systems. In this context a crucial role is played by the balancing of the work load among all nodes in the system. So far load balancing approaches have been designed for networks with fixed or dynamic topologies. These approaches work well in the case each node knows its similes and is able to contact them to delegate tasks. However, they do not address the needs of more dynamic systems where nodes are able to process different types of jobs and have limited knowledge about their neighbors and the whole system. To address these issue, we are experimenting with the usage of autonomic self-aggregation techniques that rewire such highly dynamic systems in groups of homogeneous nodes that are then able to balance the load among each others. We present our approach and show through simulation that it provides significant advantages under the circumstances described before.

iCAR is a modern wireless technology. It is based on dividing the network area into some cells (areas) and integrating the cells. In iCAR, Ad-hoc networks are dynamically distributed and self-organized cellular systems. It allows internetwork communication between the topologies without infrastructure. The main purpose of iCAR is to present new architectures to address congestion in cellular systems due to unbalanced traffic. It can effectively increase system's capacity and also can add interoperability between different networks. Here, we try to analyze whether the increasing traffic loads between the internetworking cells and limited capacity of the systems can be effectively balanced by the new architectures or not. We also interrogate how limited number of ARS stations is used for balancing congestion. We also evaluate the performance of iCAR in terms of ARS coverage.

This paper realizes the vision of Mobile Grid Computing by proposing a fair pricing strategy and an optimal, static job allocation scheme. Mobile devices has not yet been integrated into Grid computing platforms mainly due to their inherent limitations in processing and storage capacity, power and bandwidth shortages. However, millions of laptops, PDAs and other mobile devices remain unused most of the time and this huge resource repository can be potentially utilized in the Grid environment. Here, we propose a game theoretic pricing model, to address load balancing issues in mobile grids. In particular, by drawing upon the Nash Bargaining Solution (NBS), we show that we can obtain a unified framework for addressing such issues as network efficiency, fairness, utility maximization, and pricing. The advantage of this framework is that we have a precise mathematical characterization of the solutions and their properties. Our current endeavor characterizes a twoplayer alternating-offer bargaining game between the Wireless Access Point (WAP) Server and the mobile devices to determine the pricing strategy which is then used to effectively distribute jobs to the mobile devices. Our job allocation scheme maximizes the revenue of the grid user, and yet is comparable to other load balancing schemes in terms of the overall system response time.

Cloud computing is emerging as a new paradigm of large-scale distributed computing. It is a framework for enabling convenient, on-demand network access to a shared pool of computing resources. Load balancing is one of the main challenges in ...

Depending on your age, you may have seen the 80’s film Brewster’s Millions. That doesn’t sound like too much of a challenge nowadays. And so for a bit of fun in these hard times, we’ve updated the model and taken a look at 12 ways to outlandishly burn through a billion pounds.

The problem of gravity balancing of robotic systems has been investigated for a long time. A big amount of different designs has been developed so far, but with several limitations: applicability only to planar kinematics or some particular spatial ones, encumbrance and reduced workspace of the robot, complication of both theoretical and practical implementation. This chapter deepens a new simple technique for gravity balancing any spatial serial manipulator with rotational joints, using a number of springs less or equal to the number of degrees of freedom of the manipulator. Then, such technique is extended to a concept of actuation for robotic systems. Given a robotic manipulator and a force to exert at the level of the end effector, there is no energy consumption regardless of the configuration of the system (like in passive systems), as long as magnitude and orientation of the required force are fixed. Changes in magnitude and/or orientation of the exerted force require some energy to be achieved (like in active systems). Such combined features make an hybrid system with several benefits: low energy consumptions, simplified control and intrinsic safety of the system, with wide prospects in robotics.

The growing availability of low cost microprocessors and the evolution of computing networks have enabled the construction of sophisticated distributed systems. The computing capacity of these systems motivated the adoption of clusters to build high performance solutions. The improvement of the process scheduling over clusters originated several proposals of scheduling and load balancing algorithms. These proposals have motivated this work, which defines, evaluates and implements a new load balancing algorithm for heterogeneous capacity clusters. This algorithm, named Ant Scheduler, uses concepts of ant colonies for the development of optimization solutions. Experimental results obtained in the comparison of Ant Scheduler with other approaches investigated in the literature show its ability to minimize process mean response times, improving the performance.

SUMÁRIO O Calendário utilizado em nosso dia-a-dia traz em si uma História no mí-nimo interessante. Matemática, Filosofia, História, Religião. Esses são os principais ingredientes que fizeram nosso Calendário evoluir. SUMMARY The Calendar used in our day-today life brings with it a history at least interesting. Mathematics, Philosophy, History, Religion. These are the main ingredients that made our Calendar evolve. 1 Introdução É fato notório que a verdadeira duração do ano da Terra é 365,2422 dias solares médios (oficialmente, o ano tem exatos 31556943,36 s.), valor utilizado pela mai-oria dos astrônomos para os complexos cálculos que envolvem o tempo. Como não é possível trabalharmos com frações de dias no comércio, indústria, agricul-tura e outras áreas da atividade humana, nosso calendário está sincronizado com as estações do ano (em verdade, com o Equinócio de Primavera, no hemisfério Norte; a palavra vem do latim aequs, igual, e nox, noite; duração do dia igual a da noite e representa os instantes em que o Sol, em seu movimento aparente anual, atravessa o equador celeste), mantendo a maioria dos anos com 365 dias e a cada quatro anos o ano bissexto que tem 366 dias. Por razões históricas, esses 365 dias são divididos em 12 meses que têm entre 28 e 31 dias. Nota 1.: devemos distinguir dois tipos de "ano": a) Ano sideral: é o período de revolução da Terra em torno do Sol com relação às estrelas. Sua duração é de 365,2564 dias solares médios, ou 365d 6h 9min 12,96s. b) Ano tropical: é o período de revolução da Terra em torno do Sol com relação ao Equinócio Vernal, isto é, com relação ao início das estações. Sua duração é 365,2422 dias solares médios, ou  365d 5h 48min 46,08s. Devido ao movi-mento de precessão da Terra, o ano tropical é levemente menor do que o ano sideral (cerca de 20min 26,88s). Nosso Calendário é chamado de Gregoriano; está baseado no ano tropical, e possui as seguintes propriedades: 1. Os meses e as semanas incluem todos os 365 dias do ano. Isso significa que um determinado dia do ano está associado a um dia da semana, a um deter-minado mês e a um número desse mês; 2. As semanas têm sete dias, coincidindo com as tradições cristãs e judaicas entre outras; 3. Os meses coincidem com o período lunar de 29,5 dias (conceito tradicional de "mês"). Atualmente, o número exato é 29,5305889 dias (é variável e

Cloud computing is the dynamic delivery of information technology resources and capabilities as a service over the Internet. Cloud computing is a style of computing in which dynamically scalable and often virtualized resources are provided as a service over the Internet. It generally incorporates infrastructure as a service (IaaS), platform as a service (PaaS), and software as a service (SaaS). [1] Load balancing is one of the biggest challenges in the cloud computing. The concept of load balancing is to equally distribute the workload, resources across all the nodes to guarantee that all the nodes have equal load i.e. no single node is over loaded. As we all know that cloud computing services are mainly product based so in this approach we are using different product based priority queues for different services.

Workload and resource management are two essential functions provided in the service level of a Grid software infrastructure. Consistently, efficient load balancing algorithms are fundamentally important to improve the global throughput of these environments. Although previous works show that, ant colony algorithm works well for load balancing, the cost is a very important factor in this subject. In this paper, a grid load balancing algorithm is proposed by using an ant colony optimization which is able to consider shortest path, type of resource, and running speed of resource. The experimental results show that the proposed algorithm by using this ant colony optimization can reduce the cost of load balancing in comparison with standard algorithm DASUD.

This paper introduces a new IEEE standard, IEEE 802.15.5,which provides mesh capability for wireless personal area network (WPAN) devices. The standard provides an architectural framework enabling WPAN devices to promote interoperable, stable, and scalable wireless mesh topologies. It is composed of two parts: low-rate WPAN mesh and high-rate WPAN mesh. In this paper, we present only low-rate WPAN mesh because it is designed to support wireless sensor networks. IEEE 802.15.5 low-rate part is a lightweight scalable mesh routing protocol that caters well to the requirements of resource-constrained wireless sensor networks. By binding logical addresses to the network topology, IEEE 802.15.5 obviates the need for route discovery. This eliminates the initial route discovery latency, saves storage space and reduces the communication overhead and energy consumption. A distributed link state scheme is further built atop the block addressing scheme to improve the quality of routes, robustness, and load balancing. The routing scheme scales well with regard to various performance metrics. The standard also provides enhanced functions such as multicast, reliable broadcast, power saving, time synchronization, route tracing and portability. We also present the performance evaluation of major functions performed with a 50-nodes tested deployed over a whole floor (100 x 140 ft2) at CUNY Engineering building. The results testify that the IEEE 802.15.5 will serve well for wireless personal area networks and wireless sensor networks.

The non-blocking work-stealing algorithm of Arora, Blumofe, and Plaxton (henceforth ABP work-stealing) is on its way to becoming the multiprocessor load balancing technology of choice in both industry and academia. This highly efficient scheme is based on a collection of array-based doubleended queues (deques) with low cost synchronization among local and stealing processes. Unfortunately, the algorithm's synchronization protocol is strongly based on the use of fixed size arrays, which are prone to overflows, especially in the multiprogrammed environments for which they are designed. We present a work-stealing deque that does not have the overflow problem. The only ABP-style work-stealing algorithm that eliminates the overflow problem is the list-based one presented by Hendler, Lev and Shavit. Their algorithm indeed deals with the overflow problem, but it is complicated, and introduces a trade-off between the space and time complexity, due to the extra work required to maintain the list. Our new algorithm presents a simple lock-free work-stealing deque, which stores the elements in a cyclic array that can grow when it overflows. The algorithm has no limit other than integer overflow (and the system's memory size) on the number of elements that may be on the deque, and the total memory required is linear in the number of elements in the deque.

proaches can give results of large generality and accuracy. One of the models presented in the literature (that from K. H. Weck) and the model proposed in the paper allow to reach an accuracy generally much better than 10% for configurations without insulators.

We discuss algorithms for matrix multiplication on a concurrent processor containing a two-dimensional mesh or richer topology. We present detailed performance measurements on hypercubes with 4, 1,6, and 64 nodes, and analyze them in ter:'as of communication overhead and load balancing. We show that the decomposition into square subblocks is optimal C code implementing the algorithms is available.

Cloud computing is one of the most interesting research areas having great impact on technological development. This paper focuses on survey of various load balancing methods. During the recent years many load balancing approaches are proposed in the area of cloud computing. For further researches, understanding of these approaches is essential.

Writing programs (or programming) is a very creative and rewarding activity. You
can write programs for many reasons, ranging from making your living to solving
a difficult data analysis problem to having fun to helping someone else solve a
problem. This book assumes that everyone needs to know how to program, and
that once you know how to program you will figure out what you want to do with
your newfound skills.

Cloud Computing is becoming a viable computing solution for services oriented computing. Several open-source cloud solutions are available to these supports. Open-source software stacks offer a huge amount of customizability  without huge licensing fees. As a result, open source software are widely used for designing cloud, and private clouds are being built increasingly in the open source way. Numerous contributions have been made by the open-source community related to private-IaaS-cloud. OpenNebula - a cloud platform is one of the popular private cloud management software. However, little has been done to systematically investigate the performance evaluation of this open-source cloud solution in the existing literature. The performance evaluation aids new and existing research, industry and international projects when selecting OpenNebula software to their work. The objective of this paper is to evaluate the load-balancing performance of the OpenNebula cloud management software. For the performance evaluation, the OpenNebula cloud management software is installed and configured as a prototype implementation and tested on the DIU Cloud Lab. In this paper, two set of experiments are conducted to identify the load balancing performance of the OpenNebula
cloud management platform- (1) Delete and Add Virtual
Machine (VM) from OpenNebula cloud platform; (2) Mapping
Physical Hosts to Virtual Machines (VMs) in the OpenNebula
cloud platform.

امروزه صنعت پویانمایی سازی یکی از پرطرفدارترین و پر درامد ترین صنعتها محسوب میشود؛ که بخش
بزرگی از اوقات فراغت همه مردم جهان را پرکرده، چه بر روی کامپیوترهای شخصی، چه بر روی کنسولهای
بازی و حتی موبایلها که همجا به همراه داریم. ازاینرو فعالیتهای زیادی در این زمینه صورت میگیرد تا
بازیهای سرگرمکننده و متنوع را ارائه دهند. یکی از تکنیکهایی که تحول بزرگی در این صنعت ایجاد
کرده، تکنیک ردیابی پرتو در بحث تولید تصاویر گرافیکی میباشد. در سالهای گذشته تحقیقات زیادی
مبنی بر بهبود این تکنیک و کاهش زمان پردازش آن صورت گرفته. دغدغه اصلی این تکنیک زمان پردازش
آن نیز میباشد. در تلاشهای صورت گرفته تا جایی توانستهاند این زمان را کاهش دهند، اما باز نتوانستهاند
از حداکثر توان سختافزار برای کاهش این زمان استفاده کنند.در این مقاله به برسی روشهای توزیعشده و
تکی این روشها می پردازیم.

"Virtualization  technology  provides  the  ability  to  transfer  virtual  machines  (VM)  between  the  physical
systems using the technique of live migration mainly for improving the efficiency. Server consolidation through live
migration is an efficient way towards energy conservation in cloud data centers. The main objective  of this study is to
prevent  server  sprawl,  which  refers  to  the  usage  of  multiple-utilized  servers  in  data  centers  incurring  high  system
management  cost.  To prevent  server  sprawl,  server  consolidation  aims  at  reducing  the  number of  server machines
used in the data centers by consolidating load and enhancing resource utilization of physical systems. Although a lot
of  research  and  study  has  been  conducted  on  server  consolidation,  a  range  of  issues  involved  have  mostly  been
presented in isolation of each other. Therefore,  here an attempt has been made  to present a comprehensive survey  to
study the different server consolidation algorithms in a cloud computing environment."

— Cloud computing is a method or technique for enabling convenient, on demand network access to a shared pool of computing resources (such as computer networks, servers, applications, storage, and services) that can be continuously provisioned and released with minimum management efforts. In this paper we have used some of the existing performance monitoring tools and techniques popular among variety of users. During this study a number of factors such as response time, bandwidth and latency etc. have been determined. Considering the frequency of factors appearing from the review work it has been inferred that the cloud response time is very crucial for the cloud performance and selected for further study.

Green & Eco-friendly mode of travel – reduces carbon emission, fuel consumption and pollution. Faster, safer and comfortable air – conditioned travel with reduced travel time. Ultra-modern coaches. High frequency of trains- reducing waiting time. Establishing User Friendly Transport.

Cloud computing is one of the recent incredible technology which open the new vision for IT industry. At present scenario, it is becoming an strong alternative, to startup large as well as small scale industries that only uses the resources which actually required based on pay as per on pay use. As Cloud Computing is growing continuously and clients those are from different area of the world are generate demand for the various services and better results, the load balancing has the challenge for the cloud service provider. To accurately manage all the available resources of the different cloud provider. Many algorithms have been proposed to provide efficient management and fulfill the client's requests to available cloud nodes, and aim to enhance the overall performance of the cloud services and provide more satisfaction to requested user. This paper gives an introduction about cloud computing and load balancing and detailed survey on different types of load balancing policy in cloud analyst, their merits and demerits with reasonable solution and learn how to add new approach with existing load balancing policy.

We propose, design, and construct a smart load management (SLM) system that can be effectively utilized to meet up emergency demand (light and fan) of consumers when power generation is not sufficient with respect to its demand. The connectivity among power distribution authority, SLM device, and user are established by authority identification number, de­ vice identification number, and user identification number using GSM-based mobile network. The SLM device can be configured and reconfigured load simply by SMS without changing hardware or software. Using the device, the power distribution authority will be able to provide power for emergency loads of all con­ sumers and also to monitor maximum allowable permitted load. Instead of complete blackout, SLM device facilitates switching over from permitted load to emergency and vice versa depending on the availability of the power supply. The SLM system can be effectively applied in a country where demand of electricity is more than its generation.

Thermal load is defined as the high temperature that causes the effect on any structure, such as outdoor air temperature, solar radiation, underground temperature, indoor air temperature and the heat source equipment inside the building or material storage tanks with variation in temperature. The basic thermal load is the 100-year-return period of transform in outdoor air temperature, solar radiation, underground temperature or equivalent value. Performance of any structure as soon as exposed to fire depends on the material properties and in-barriers to withstand or to confine fire, Concrete structures be capable to have enormous performance for the duration of fire event if the concrete has lower thermal conductivity which leads to slower increase of the concrete temperature. For steel structures, strength, ductility, consistency of the steel material, shape of the structure and the applied load are significant factors which should be observed for fire resistance calculation. The critical/essential temperature depends on the load ratio and steel composition.

This study was conducted on the importance of performance testing of web applications and analyzing the bottleneck applications. This paper highlights performance testing based on load tests. Everyone wants the application to be very fast, at the same time, reliability of the application also plays an important role, such that user's satisfaction is the push for performance testing of a given application. Performance testing determines a few aspects of system performance under the pre-defined workload. In this study JMeter performance testing tool was used to implement and execute the test cases. The first load test was calculated with 200 users which was increased to 500 users and their throughput, median, average response time and deviation were calculated.

Performance Testing, is a type of testing performed to check how application or software performs under workload in terms of responsiveness and stability. The primary Goal is to identify and remove Performance bottlenecks from an application. This test is mainly performed to check whether the software meets the expected requirements for application speed, scalability, and stability. Providing the service of more than 20000 trains every day, Indian Railways is one of the world's busiest rail networks. Carrying more than 2,00,00,000 crore people every day, More than 6,00,000 ticket booking is made through online. So to measure performance of the system there is a need for performance testing. To ensure the performance of the system with more number of transactions, this testing is performed using any one of the performance testing tools. In this system, IRCTC web site as a Case study and this site is tested with more than 1,00,000 virtual users and its performance is shown with the help of Graphical charts. It can be used to simulate a heavy load on a server or group of servers, database, or network to test its strength, or to analyze overall performance under different load types.

In this study, a cluster-computing environment is employed as a computational platform. In order to increase the efficiency of the system, a dynamic task scheduling algorithm is proposed, which balances the load among the nodes of the cluster. The technique is dynamic, nonpreemptive, adaptive, and it uses a mixed centralised and decentralised policies. Based on the divide and conquer principle, the algorithm models the cluster as hyper-grids and then balances the load among them. Recursively, the hyper-grids of dimension k are divided into grids of dimensions k − 1, until the dimension is 1. Then, all the nodes of the cluster are almost equally loaded. The optimum dimension of the hyper-grid is chosen in order to achieve the best performance. The simulation results show the effective use of the algorithm. In addition, we determined the critical points (lower bounds) in which the algorithm can to be triggered. 2 System Model & Hyper-Grids A Computational Cluster (CC) is a collection of independent processing-nodes interconnected by a network. We as

ABSTRAK
Pada masa sekarang ini teknologi informasi terutama pada jaringan internet berkembang sangat pesat. Dan seiring dengan perkembangan teknologi dan ilmu pengetahuan, tingkat kebutuhan masyarakat akan informasi dalam bermasyarakat semakin tinggi. Pada penerapannya jaringan yang biasa digunakan saat ini hanya menggunakan switch, dimana kekurangan menggunakan switch adalah pada saat bersamaan user user yang menggunakan koneksi internet akan saling memperebutkan bandwith dan berakibat tidak balance nya kecepatan pada masing masing user. Pada penulisan ini penulis ingin mencoba merancang pc router menggunakan ClearOS.
ClearOS adalah system operasi berbasis Linux.Pengaturan Bandwidth adalah pengalokasian yang tepat dari suatu bandwidth yang tersedia untuk mendukung kebutuhan atau keperluan aplikasi suatu layanan jaringan. MultiWan atau load balancer adalah metode penggabungan beberapa line internet.Dalam hal ini sifatnya adalah menyeimbangkan beban trafik di setiap line internet yang ada sehingga pemanfaatannya bisa merata. Untuk dapat melakukan konfigurasi tersebut dilakukan pada sistem operasi Linux dengan menggunakan Command Line Interface (CLI). ClearOS adalah Linux server yang distribusikan berdasarkan CentOS dan Red Hat Enterprise Linux, di desain khusus untuk keperluan gateway dan server pada perusahaan kecil dan menegah dengan menggunakan sistem administrator berbasiskan Graphical User Interface (GUI). Selain itu digunakan aplikasi webHTB sebagai tools untuk mengatur bandwidth dan prioritas langsung pada traffik contol pada kernel Linux ClearOS berbasikan GUI. Dengan mengimplementasikan metode Hierarchical Token Bucket (HTB) pada sistem operasi ClearOS diharapkan menjadikan jaringan yang menerapkan Bandwidth manajemen sistem ini dapat mengatur bandwidth dan prioritas bandwidth dengan baik. Pengujian dilakukan dengan cara pembatasan bandwidth dan merubah index prioritas dengan beberapa client. Hasil pengujian webHTB terhadap Linux ClearOS menunjukan bahwa nilai prioritas pada metode Load Balancing atau MultiWan memegang peranan paling besar untuk kecepatan pada client. Dimana bandwidth menetukan nilai transfer rate minimal.
Kata Kunci : Pengaturan Bandwidth, Load Balancer,Multi Wan, Priority Service (PS), ClearOS
ABSTRACT
At the present time , especially information technology on the Internet is growing very rapidly . And along with the development of technology and science , the level of community need for the information in the higher society . In practice commonly used network is currently only using the switch , which shortfall using switches at the same time the user is a user who uses the internet connection will be vying for bandwidth and balance its repercussions on the speed of each user . In this paper the authors want to try to design a pc router using ClearOS .
ClearOS is a Linux-based operating system .Bandwidth settings are appropriate allocation of the available bandwidth to support the needs or purposes of the application of a network service . MultiWAN or load balancaer is a method of combining several line internet.Dalam this nature is balancing the traffic load on any existing internet line so that utilization can be evenly distributed . To be able to perform the configuration is done on the Linux operating system using the Command Line Interface ( CLI ) . ClearOS is a Linux server that is distributed based on CentOS and Red Hat Enterprise Linux , specifically designed for the purposes of gateways and servers in small and medium enterprises by using a system administrator based Graphical User Interface ( GUI ) . Also used as a tool webHTB application to set the bandwidth and priority at traffic contol directly on the Linux kernel berbasikan ClearOS GUI . By implementing the methods Hierarchical Token Bucket ( HTB ) on ClearOS operating system is expected to make the network bandwidth management that implements this system can manage the bandwidth and priority bandwidth well . Testing is done by limiting the bandwidth and priority index change with a few clients . The test results on the Linux ClearOS webHTB shows that the priority value on Load Balancing method or MultiWAN greatest role to speed on the client . Where bandwidth determines the minimum value of the transfer rate.
Keywords: Bandwidth Settings, Load Balancer, Multi Wan, Priority Service (PS), ClearOS

Abstrak Jaringan komputer adalah hal yang sudah harus ada pada kantor-kantor saat ini, kebutuhan internet sangatlah tinggi untuk menunjang kegiatan maupun pekerjaan agar menjadi jauh lebih efisien. Di kantor yang terdapat banyak karyawan maupun sub bagian pastilah memiliki situasi kerja yang berbeda, meskipun telah ada limitasi pada setiap bagian maupun setiap komputer/device, namum tetap saja masalah kebutuhan bandwidth kadang masih tetap terjadi, entah itu dikarenakan banyaknya pengguna yang menggunakan jaringan tersebut maupun beberapa pengguna yang menggunakan jalur tersebut untuk internet demi menunggu pekerjaan berikutnya tiba. Dengan menggunakan Mark Routing memungkinkan mikrotik untuk memberikan sebuah tanda/mark pada setiap koneksi dan paket data yang lewat untuk nantinya dapat diatur sedemikian rupa saat melalui jaringan router tersebut, dalam penelitian ini dilakukan pemindahan koneksi yang menuju server dan akses website penunjang pekerjaan akan dialihkan menuju jalur akses gateway ISP2. Diterapkan pula data priority guna memprioritaskan jalur akses kepada paket data penting ketika banyak data melewati jalur akses yang sama dan penggunaan failover untuk mengatasi kegalalan koneksi ketika salah satu jalur akses mati. Dari penerapan 3 teknik diatas didapatkan hasil berupa thoughput yang jauh meningkat dan response time berkurang rata-rata sebesar 68,1% serta pengalihan gateway pada client ketika mengakses website tertentu yang telah ditentukan agar menuju gateway ISP2. Kata kunci: Failover , Jaringan, Mark Routing, Prioritas Data, Switching. Abstract Computer networks are things that must already exist in offices today, the internet is needed to support activities and work to be much more efficient. In an office where there are many employees and subsections , there must be different work situations, even though there are limitations on each part and every computer/device, but still the problem of bandwidth needs occurs, whether it's because so many users who use the network or some users who surfing internet to wait for the next job to arrive. Using the Mark Routing allows the proxy to provide a mark on each connection and data packets that pass to be able to arrange in such a way through the router network, In this research, the connection to the server and connection to website that support the work will be is separated and transferred into ISP2 gateway. Data priority is also applied to prioritize access line for important data packages when a lot of data passes through the same line and using failover to overcome connection failure when one of the gateways dies. From implementing 3 techniques that has ben said giving increased throughput and reduced response time by an average of 68.1%, also gateway will be switching when client access some of the website that has been listed to use ISP2 gateway.

Seiring meningkatnya kebutuhan kehandalan layanan Teknologi Informasi dan Komunikasi (TIK) untuk menjalankan proses bisnis yang kritikal bagi organisasi, maka diperlukan upaya untuk terus menjaga dan meningkatkan performansi dan availability bagi penyedia layanan TIK. Salah satu upaya yang dilakukan adalah dengan meletakkan suatu sistem/aplikasi yang kritikal tidak hanya di dalam satu Data Center (DC) tetapi juga di di Data Center (DC) lain yang berbeda lokasi atau di Disaster Recovery Center (DRC). Dengan meletakkan sistem/aplikasi di lokasi Data Center (DC) yang berbeda atau Disaster Recovery Center (DRC), diharapkan apabila terjadi gangguan pada Data Center (DC), layanan masih dapat berjalan. Namun perpindahan dari DC ke DRC seringkali terkendala dengan waktu perpindahan yang relatif lambat, sehingga menjadi issue bagi layanan yang sangat kritikal. Salah satu teknologi yang dapat mempersingkat waktu perpindahan dari DC ke DRC adalah Global Server Load Balancing (GSLB) atau dikenal sebagai smart/intelligent DNS (Domain Name System). Teknologi ini bahkan dapat digunakan untuk melakukan distribusi traffic secara aktif-aktif pada lokasi DC yang berbeda. Proyek implementasi Global Server Load Balancing (GSLB) diharapkan mampu memangkas waktu perpindahan dari DC ke DRC, bahkan ke depannya diharapkan dapat mendukung implementasi konfigurasi aktif-aktif antara DC dan DRC. Keywords: distribusi trafik, GSLB, Global Server Load Balancing, smart DNS, waktu propagasi DNS I. PENDAHULUAN Perkembangan kebutuhan Teknologi Informasi dan Komunikasi (TIK) mendorong meningkatnya kebutuhan kehandalan layanan secara kontinu sehingga sistem TIK yang ada dituntut tidak boleh mengalami gangguan maupun kegagalan yang berdampak pada terganggunya layanan proses bisnis yang ada. Untuk menjaga kehandalan layanan TIK yang ada, maka selain kebutuhan sistem dalam Data Center, diperlukan juga Disaster Recovery Center untuk memberikan kehandalan layanan yang lebih baik. Kementerian Keuangan (Kemenkeu) saat ini telah memanfaatkan secara massif dan intensif layanan Teknologi Informasi dan Komunikasi untuk mendukung proses bisnis pengelolaan keuangan dan kekayaan Negara secara terpadu. Terdapat berbagai sistem kritikal yang harus dijaga kehandalannya selama 24 jam setiap hari. Untuk menjaga kehandalan, performansi, dan kapasitas, maka selain di Data Center (DC), sistem-sistem TIK yang kritikal juga diletakkan pada Disaster Recovery Center (DRC). Saat ini konfigurasi pada DC dan DRC tidak bersifat aktif-aktif, namun bersifat aktif-standby. Apabila terjadi gangguan yang massif pada sistem yang aktif (DC) pada sistem akan berpindah ke DRC. Perpindahan sistem dari DC ke DRC masih dilakukan secara manual dalam artian masih memerlukan perubahan konfigurasi yang dilakukan secara manual. Untuk mewujudkan layanan TIK yang resilent dengan memanfaatkan potensi DC dan DRC, selain kesiapan sistem-sistem TIK itu sendiri, maka diperlukan teknologi yang dapat meminimalkan perubahan yang harus dilakukan ketika terjadi perpindahan sistem dari DC ke DRC. Salah satu perubahan yang harus dilakukan pada saat pemindahan sistem dari DC ke DRC adalah perubahan yang dilakukan pada Domain Name System (DNS). DNS ini adalah sistem yang menyimpan informasi nama host atau nama domain dan alamat IP atau dengan kata lain DNS adalah layanan yang menerjemahkan nama dari situs web menjadi alamat internet (IP Address). Perubahan konfigurasi di DNS perlu dilakukan untuk mengubah mapping nama domain yang semula memiliki alamat.

Keywords: distribusi trafik, GSLB, Global Server Load Balancing, smart DNS, waktu propagasi DNS

As we know that in distributed systems several autonomous computers are interconnected to provide a single coherent view of a powerful system and these autonomous computers work independently in a team-like fashion such that the domain of tasks is shared between all of them. Now to take full advantage of this distributed scenario, we need good resource allocation schemes. Load distribution algorithm's work is to deliverately distributed and re-distributes the tasks (loads) among all the participating nodes so that the overall performance of the entire system is maximized. in this paper we study the details of the load distribution algorithms and their suitableness in various load scenerios.

Load balancing is a composition of methods to distribute workload among multiple networks or network components such as links, processing units, storage devices, and users to achieve optimality in respect to resource utilization, maximum throughput and minimum response time. It also helps to avoid overload and provide Quality of Service (QoS). In a situation where multiple resources are available for a particular functionality, load balancing can be used to maximize network efficiency and increase fairness in network resource usage while keeping a balance between QoS and resource usage.

Cloud computing is emerging as a new paradigm of large-scale distributed computing. It is a framework for enabling convenient, on-demand network access to a shared pool of computing resources. Load balancing is one of the main challenges in cloud computing which is required to distribute the dynamic workload across multiple nodes to ensure that no single node is overwhelmed. It helps in optimal utilization of resources and hence in enhancing the performance of the system. The goal of load balancing is to minimize the resource consumption which will further reduce energy consumption and carbon emission rate that is the dire need of cloud computing. This determines the need of new metrics, energy consumption and carbon emission for energy-efficient load balancing in cloud computing. This paper discusses the existing load balancing techniques in cloud computing and further compares them based on various parameters like performance, scalability, associated overhead etc. that are conside...

—Datacenters provide cost-effective and flexible access to scalable compute and storage resources necessary for today's cloud computing needs. A typical datacenter is made up of thousands of servers connected with a large network and usually managed by one operator. To provide quality access to the variety of applications and services hosted on datacenters and maximize performance, it deems necessary to use datacenter networks effectively and efficiently. Datacenter traffic is often a mix of several classes with different priorities and requirements. This includes user-generated interactive traffic, traffic with deadlines, and long-running traffic. To this end, custom transport protocols and traffic management techniques have been developed to improve datacenter network performance. In this tutorial paper, we review the general architecture of datacenter networks, various topologies proposed for them, their traffic properties, general traffic control challenges in datacenters and general traffic control objectives. The purpose of this paper is to bring out the important characteristics of traffic control in datacenters and not to survey all existing solutions (as it is virtually impossible due to massive body of existing research). We hope to provide readers with a wide range of options and factors while considering a variety of traffic control mechanisms. We discuss various characteristics of datacenter traffic control including management schemes, transmission control, traffic shaping, prioritization, load balancing, multipathing, and traffic scheduling. Next, we point to several open challenges as well as new and interesting networking paradigms. At the end of this paper, we briefly review inter-datacenter networks that connect geographically dispersed datacenters which have been receiving increasing attention recently and pose interesting and novel research problems. To measure the performance of datacenter networks, different performance metrics have been used such as flow completion times, deadline miss rate, throughput and fairness. Depending on the application and user requirements, some metrics may need more attention. While investigating different traffic control techniques, we point out the trade-offs involved in terms of costs, complexity and performance. We find that a combination of different traffic control techniques may be necessary at particular entities and layers in the network to improve the variety of performance metrics. We also find that despite significant research efforts, there are still open problems that demand further attention from the research community.

Abstrak Load balancing merupakan salah satu masalah yang terdapat di dalam jaringan. Permintaan user yang melebihi kapasitas dalam satu waktu menyebabkan overload yang dapat menyebabkan kondisi server down karena matinya web server sehingga menyebabkan banyak user tidak dapat terlayani. Hal ini juga bisa disebabkan oleh kondisi server yang heterogen dipaksa dalam menerima request dari user tanpa adanya strategi load balancing untuk mengatasi permasalahan tersebut. Software Defined Network membuat paradigma baru dalam menyelesaikan masalah load balancing pada jaringan tradisional. SDN Load Balancer memberikan fasilitas untuk membangun dan merancang strategi load balancing yang fleksibel dan bisa diprogram sesuai kebutuhan. Algoritma Weighted Round Robin dan Weighted Least Connection memiliki kemampuan menyeimbangkan beban dan mempertimbangkan kapasitas server dengan menentukan jumlah bobot ke masing-masing server. Pengujian performansi dilakukan dengan simulasi jaringan virtual SDN menggunakan mininet dan http server sederhana. Hasil pengujian response time, weighted round robin mengungguli weighted least connection dengan rata-rata response time terkecil 39.7 msec. Pada pengujian throughput, weighted least connection mendapat hasil tertinggi sebesar 57,1 MB/sec. Dan pada pengujian cpu utilization kedua algoritma berhasil membagi kinerja server dengan baik, dan weighted round robin mempunyai persentase penggunaan server lebih tinggi yaitu server 1 dengan nilai 36.6%, server 2 37,3% dan server 3 sebesar 38,1%. Kata kunci : Load Balancing, Weighted Round Robin, Weighted Least Connection, Software Defined Network. Abstract Load balancing is one of the problems found in the network. User requests that exceed capacity at one time cause overload that can cause server conditions to be down due to the death of the web server, causing many users to be underserved. This can also be caused by heterogeneous server conditions that are forced to accept requests from users without a load balancing strategy to overcome these problems. Software Defined Network creates a new paradigm in solving load balancing problems on traditional networks. SDN Load Balancer provides facilities to build and design flexible and programmable load balancing strategies as needed. Weighted Round Robin Algorithm and Weighted Least Connection Algorithm has the ability to be able to balance the load and consider server capacity by determining the amount of weight to each server. Performance testing with simulations of SDN-based virtual networks. The response time, weighted round robin test results outperformed the weighted least connection with the smallest average response time of 39.7 msec. In testing throughput, the weighted least connection gets the highest yield of 57.1 MB / sec. And the cpu utilization test both algorithms managed to divide server performance well, and weighted round robin had a higher percentage of server usage, namely server 1 with 36.6%, server 2 37.3% and server 3 at 38.1%.

Cloud Computing refers to the use and access of multi ple server based computational resources via a digital network(WAN).Cl oud users may access the resources using computer note book, pad computer, smart phone, or other device. In cloud computing applications are provi ded and managed by the cloud server and data is also stored remotely in cloud configuration. As Cloud Computi ng is growi ng rapi dly and clients are demanding more services and better results, load balancing for the Cloud has become a very interesting and i mportant research area. Load bal ancing ensures that all the processor in the system or every node i n the network does approxi mately the equal am ount of work at any instant of ti me. Here in this paper we have discussed many different load balancing techni ques used to sol ve the issue in cloud computing environment. This paper presents various approaches given by the researchers using the load balancing techni ques.

This paper presents performance analysis of high availability concept based on traffic segregation over Multi-Protocol Label Switching (MPLS) Traffic Engineering (TE). Recent years presents many deployment of Virtual Public Network (VPN) over Multi Protocol Label Switching (MPLS) network. This deployment benefits an organization or group of business for their own private network at a much lower costs compared to traditional point-to-point (P2P) private link. Hence, enterprise benefits from the VPN in reducing cost, increasing scalability and increasing productivity without costing the security of their network. Basic requirement of today systems on the design enterprise network is high availability. Deployment of high availability in load balancing and redundancy on existing service provider backbone network is still a challenging task. This paper presents ensured implementation on the network traffic. It immediately segregates and transparent to customer when the network edge device or access circuit was failures. Virtual Router Redundancy Protocol (VRRP) is configured to support high availability. Two gateways are provided at customer edge router, where one router elected as primary gateway, and another as a standby gateway. This situation presents the backup link which is not fully utilized. Traffic diversity concept is used where Policy Based Routing (PBR) handles the traffic segregation to utilize the traffic at both links. Results on analyzed implementation of high availability concept based on traffic segregation over MPLS-TE are presented.