Earticle

Load balancing is a major challenge in heterogeneous networks (HetNets) consisting of 5G and 6G ultra-dense small cells with long-term evaluation advanced (LTE-A) networks. A key factor in achieving efficient load balancing during user mobility is creating appropriate optimisation for handover control parameters (HCP). This paper proposes a coordinated load balancing algorithm for LTE-A/fifth generation (5G) HetNets. The algorithm automatically optimises HCP settings for a given user based on three bounded functions (the signal-to-interference-plus-noise ratio (SINR) of the user equipment (UE), the number of physical resource blocks (PRBs) per UE and the UE’s speed) as well as their automatic weight levels. A two-step target cell determination strategy is implemented according to the cell load level and RSRP criteria, ensuring that users are handed over to low-loaded target cells. A new HO procedure that considers the pilot signal power is also proposed, which includes the number of PRBs per UE and the RSRP. Cells with freer PRBs are prioritised in user association to provide load balance and enhanced throughput. The proposed load balancing algorithm is compared with five other load balancing algorithms selected from the literature. The simulation results reveal that under various mobile speed scenarios, the proposed load balancing scheme enhances network performance in terms of load level, throughput, spectral efficiency and call dropping ratio (CDR).

In cloud computing systems the continuous increasing need for a variety of applications has made workload distribution and resource allocation more difficult. These difficulties lead to a high degree of imbalance and poor system performance. To address these issues, this study presented a high scalable Improved Multi-Objective Hybrid Load Balancing (IMH_LB) Algorithm. It combines the Grey Wolf Optimization (GWO) algorithm with the velocity driven approach of Particle Swarm Optimization (PSO) technique. The suggested method has been developed to optimize cloud computing environments by improving resource utilization with high scalability. The quality-of-service (QoS) parameters are comparatively analyzed in CloudSim by benchmarking the proposed algorithm against standard (GWO and PSO) algorithms and state of the art (Hybrid GWO-PSO and Improved Hybrid Genetic Algorithm-GWO) algorithms. The experimental findings show the superiority of the proposed approach with average improvements of 72.16% in average response time, 67.27% in makespan, 5.18 times in throughput, in 7.51 times in average resource utilization and 78.51% in degree of imbalance over the standard (GWO and PSO) and state of the art (HGWO-PSO and IHGA-GWO) methods. The proposed algorithm achieves high scalability while stabilizing at an average utilization of 89 % at significantly high workloads.

As a solution to spectrum under-utilization problem, Cognitive radio (CR) introduces a dynamic spectrum access technology. In the area, one of the most important problems is how secondary users (SUs) should choose between the available channels, which means how to achieve load balancing between channels. We consider spectrum load balancing problem for CR system in frequency domain and especially in time domain. Our objective is to balance the load among the channels and balance the occupied time length of slots for a fixed channel dynamically in order to obtain a user-optimal solution. In frequency domain, we refer to Dynamic Noncooperative Scheme with Communication (DNCOOPC) used in distributed system and a distributed Dynamic Spectrum Load Balancing algorithm (DSLB) is formed based on DNCOOPC. In time domain, Spectrum Load Balancing method with QoS support is proposed based on Dynamic Feed Back theory and Hash Table (SLBDH). The performance of DSLB and SLBDH are evaluated. In frequency domain, DSLB is more efficient compared with existing Compare_And_Balance (CAB) algorithm and gets more throughput compared with Spectrum Load Balancing (SLB) algorithm. Also, DSLB is a fair scheme for all devices. In time domain, SLBDH is an efficient and precise solution compared with Spectrum Load Smoothing (SLS) method.

본 논문에서는 사물인터넷을 증착 순서 공정에 적용하여 증착 공정을 진행하는 과정의 제어에 온도제어기, 압력제 어기, 가스제어기, 입출력 제어기 등 네 가지 종류를 대체하여 개선된 순서제어에 따른 부하균등을 해석하였다. 먼저 증착 설비에서 사물인터넷의 적용 전과 후의 시퀀스 절차를 통해 각각의 기능을 갖는 온도제어기, 압력제어기, 가스제어기, 입 출력 제어기로 제어에 필요한 데이터를 전송받아서 개선된 시퀀스 순서대로 실행을 비교하여 순서과정을 제안하였다. 또 한, 증착 공정에서 사물인터넷의 도입 전과 후를 비교하면서 증착 공정의 시퀀스 다이어그램을 작성하여 증착과정의 센싱 영역에 대한 부하 균등을 수행하였다. 이를 위해 각 센서입출력을 랜덤 프로세스와 버스트 프로세스 도착으로 모델링하고 CPU 부하와 메모리 부하를 수행한 결과를 도출하였다. 결과적으로 증착설비의 증착 공정에 장비제어기에서 수행하던 일부 기능을 사물인터넷에서 수행함으로써 장비제어기의 부하 균등 조절로 부하를 감소시키고 순서제어의 감소로 신뢰성은 높 아지는 결과를 확인하였다. 본 논문을 통해 확인한 바와 같이, 사물인터넷을 증착 공정에 적용하면 설비의 확장 시에도 장비제어기의 부하를 최소화 함으로써 설비의 안정성을 향상시킬 수 있을 것을 것으로 기대된다.

In this paper, four types of deposition control processes such as temperature, pressure, input/output(I/O), and gas were replaced by the Internet of Things(IoT) to analyze the data load and sequence procedure before and after the application of it. Through this analysis, we designed the load balancing in the sensing area of the deposition process by creating the sequence diagram of the deposition process. In order to do this, we were modeling of the sensor I/O according to the arrival process and derived the result of measuring the load of CPU and memory. As a result, it was confirmed that the reliability on the deposition processes were improved through performing some functions of the equipment controllers by the IoT. As confirmed through this paper, by applying the IoT to the deposition process, it is expected that the stability of the equipment will be improved by minimizing the load on the equipment controller even when the equipment is expanded.

클라우드 서비스가 보편화되면서 클라우드 컴퓨팅의 사용환경과 성능에 대한 관심이 급증하고 있다. 계층적으로 구성되는 클라우드 컴퓨팅 아키텍처에서 각 계층의 성능이슈가 복잡하게 연관되어 서비스 품질을 결정한다. 다양한 클라우드 응용서비스와 계층적 아키텍처를 설계하거나 평가할 때 시 뮬레이터를 이용하여 성능을 예측한다. 본 논문에서는 대규모 클라우드 응용의 성능분석 도구인 CloudAnalyst 시뮬레이터[6]에 동적 부하분산 기법을 추가, 구현하여 클라우드 컴퓨팅 서비스의 성 능분석 환경을 확장하였다. 가상머신의 사용상태를 동적으로 반영하는 하이브리드-가상머신할당 기법 을 제안하고 가상머신 별로 사용자요청이 할당되는 패턴과 응답시간을 측정, 분석하였다. SNS와 웹 서비스 응용을 대상으로 ESCE, Throttled, 하이브리드, 가상머신할당 기법과 비교한 결과 제안한 기 법이 클라우드 서비스의 성능 평가에 유용함을 확인하였다.

As cloud services have gained widespread interests in IT industry, the importance of the cloud computing performance has been increased. In the hierarchical configuration of a cloud computing, each layer poses its associated performance issues where the determination of the quality of service becomes complicated. The simulators are widely used for predicting the cloud performance in the design and evaluation of the various cloud architectures and applications. In this paper, we propose a dynamic load balancing technique that is implemented and integrated into CloudAnalyst simulator[6] as a functionality of load balancing. Proposed Hybrid VM-Assign technique can dynamically adapt to virtual machines states. Using the extended simulator the allocation pattern and the response time of user requests are measured and analyzed. The proposed method was performed on SNS and WEB applications and the comparative study with the ESCE, Throttled, Hybrd, and VM-Assign was also carried out. From the performance comparison, we validated that the proposed technique is comparable to other methods and can be efficiently used for the performance analysis of Cloud service.

무선센서네트워크(WSN)는 다양한 환경에서 정보수집을 목적으로 하는 응용분야에 널리 사용된다. WSN을 구성하는 센서노드는 저 전력 배터리를 기반으로 동작하므로 이를 고려한 WSN 수명연장은 중요한 연구목표이다. 본 논문은 효율적인 WSN을 구성하기 위해 노드의 에너지 소비는 적으면서도 클러스터 부하 균등화를 이룰 수 있는 최적화된 클러스터링 프로토콜을 제시한다. 프로토콜의 핵심 아이디어는 센서노드가 저장할 수 있는 정보용량의 한 계치를 이용해서 클러스터 멤버노드와 클러스터 밀집도가 균등분포(load balancing)되도록 하는 것이다. 또한 최적 클 러스터 헤드 확률모델을 도입해서 WSN을 분할하는 클러스터가 최적화 되도록 한다. 이를 통해서 네트워크 부하의 적절한 분산과 에너지 소비 효율을 극대화하는 성능개선을 이끌어 낼 수 있다. 성능평가 결과 제안하는 프로토콜은 대표적인 계층형 프로토콜인 LEACH와 최근에 제안된 클러스터 기반 지역 멀티 홉 라우팅 프로토콜(CBLM)보다 더 수명이 연장되고 안정화 될 수 있었다.

The Wireless sensor network(WSN) consisting of a large number of sensors aims to gather data in a variety of environments. The sensor nodes operate on battery of limited power. so, To extend network life time is major goals of research in the WSN. In this paper, we state the key point of a energy consumption with minimum&load balancing. The proposed protocol guarantee balance of number of cluster member nodes using the node memory threshold and optimization of distribution of cluster head using the optimized clustering method. The results show that the proposed protocol could support the load balancing and high energy efficiency by distributing the clusters with a reasonable number of member nodes. The simulation results show that our schme ensure longer life time in WSN as compare with existing schemes such as LEACH and CBLM.

VPN(Virtual Private Network)과 DSL, 케이블과 같은 다이얼업 접속의 조합은 저렴한 비용으 로 임대라인 기반의 사설망의 대안이 되고 있다. VPN 장비의 고가용성(High Availability, HA) 에 대한 기업의 요구가 증대되고 있다. 본 논문에서 VPN 게이트웨이에서 링크 이중화를 통한 액티브-액티브 방식을 이용해 네트웍 접근성의 고가용성과 네트웍 부하 분산 기법을 제안한다. 네트웍 링크의 고가용성/부하분산은 외부 내트웍 접근을 독립적인 두 개의 라인으로 이중화하는 것으로 달성할 수 있다. 이것은 둘 중 하나의 링크에 문제가 발생하더라도 내부 사용자에게 지 속적인 네트웍 접근을 제공할 수 있다. 뿐만 아니라, 네트웍 부하를 두 개의 라인으로 분산시킴 으로써 두 배에 가까운 네트웍 대역폭을 제공할 수 있다. 네트웍 링크의 부하 분배를 위해 정적 인 알고리즘과 동적인 알고리즘을 제안한다.

combination of VPNs and dial-up access, such as DSL and Cable, usually provides the costeffective solution as the substitution of private networks on high-cost leased line. The business demand for high availability has increased with VPN spreading. This paper presents the schemes for a high availability of network access and a load balancing of network traffic in VPN gateways by using multiple links or multihoming capability based on active-active approach. The high availability and load balancing of network links can be achieved by duplicating external network access into multiple independent links. This can provide a continuous network connection to internal users even if one of the links is failed. Moreover, it can provide twice network bandwidth by distributing the traffic into the links. Static and dynamic algorithms are proposed as the load balancing algorithms.

악성 코드로 인한 피해에 적극 대응하기 위해서는 클라이언트가 아닌 서버 측에서 실행되는 안티바이러스 소프트웨어가 필요하다. 그러나 서버용 안티바이러스 소프트웨어로 인하여 서버의 부하가 가중되는 것은 바람직하지 않다. 본 논문에서는 모니터/에이전트 구조로 멀티프로세서 환경의 서버 시스템에서 수행되는 안티바이러스 소프트웨어를 개발하였다. 이 소프트웨어는 안티바이러스 엔진의 주요 특징을 반영하여 서버에서 동적 부하 균형을 지원해줌으로써 효율적인 수행 환경을 제공한다. 악성코드 검색율과 검색 속도에 대한 성능 측정 결과는 서버용 안티바이러스 소프트웨어로서의 장점과 특징을 입증해준다.

It is more desirable to execute AV software on server systems rather than on clients for the minimization of damages due to malicious codes. AV software on server system, however, may aggravate the load of server system. In this paper, we propose a new AV software executed on server system without additional loads with a monitor and multi-agent model. The new AV software supports dynamic load balancing that reflects the features of AV engine, and thus it can be executed efficiently on server systems. The results of performance evaluation on the AV software attest to the strong points of the new AV software.

최근 멀티코어 프로세서가 널리 활용되고 있지만 프로그래머가 최적의 성능향상을 가지는 프로그램을 작성하기는 매 우 어렵다. OpenMP는 디렉티브의 삽입만으로 병렬화가 가능하지만, 최종 병렬 코드의 성능 향상은 쓰레드의 수와 쓰레드 간 작업의 분배에 크게 영향을 받는다. 본 논문은 쿼드 트리 기반 쿼리 처리 문제를 배열 기반의 트리로 변환 하여 지역성을 향상하고 자료구조의 특성에 맞게 병렬화를 진행한다. 병렬화 진행 시 동적 로드 밸런싱 기법을 통해 각 쓰레드에서 처리되는 데이터의 양을 균형적으로 할당함으로써 성능향상을 이루어내는 방법을 제안한다. 배열 기반의 쿼드 트리 데이터베이스쿼리 검색 프로그램에 동적 로드 밸런싱 기법과 병렬화를 적용한 결과를 이용 하여 쓰레드의 수와 프로그램 성능의 상관관계를 분석하고 수식화 한다. 쓰레드의 수에 따른 프로그램의 전체 수행 시간을 예상한 후 실제 수행시간과 비교할 경우 평균적으로 전체 수행시간에서 5~10%의 차이를 보인다. 이를 이용하여 최적의 성능향상을 보이는 쓰레드의 수를 예측 할 수 있다.

Recently multicore processors have been widely used, however it is still very difficult to achieve optimal performance improvement by parallel programming on multi core processors. OpenMP provides reliable parallel programming interfaces which enables parallelism by the insertion of directives; nevertheless the performance of final parallel code will be determined by the number of threads and the distribution of workload between threads. In this paper, we improve locality and parallelize quad-tree based query problems by transforming tree into array-based tree. In the process of parallelization, we propose dynamic load balancing method which enables load balance between multiple threads to implement parallelized query process on tree. The experimental results shows that proposed methods successfully parallelize the tree traversal and dynamically balance the load between threads. We also analyze experimental results to correlate number of threads and performance improvement to establish performance estimation formula. The estimated execution time of program using number of threads and the actual execution time have 5-10% gap on average. We can predict the number of threads that is optimal performance improvement using the result.

This paper designs and implements a high availability clusters and incorporated with load balance infrastructure of web servers. The paper described system can provide full facilities to the website hosting provider and large business organizations. This system can provide continuous service though any system components fail uncertainly with the help of Linux Virtual Server (LVS) load-balancing cluster technology and combined with virtualization as well as shared storage technology to achieve the three-tier architecture of Web server clusters. This technology not only improves availability, but also affects the security and performance of the application services being requested. Benefits of the system include node failover overcome; network failover overcome; storage limitation overcome and load distribution.

Cloud computing is an internet based technology. This computing paradigm has increased the utility of network where the potentiality of one node can be used by Other node, cloud provides services on demand to distributive resources such as Database, servers, software, infrastructure etc. in pay per use basis, load balancing is One of the unique and important issues for distributing a larger processing lode to smaller processing nodes for increasing total performance of system, in load balancing method the workload not only distribute across multiple computers but also other resources over the network links to gain optimum resource utilization, minimum average response time and avoid overload condition. Different load balancing algorithms have been launched in order to manage the resources of service provider efficiently and effectively. The objective of this paper is to propose efficient scheduling algorithm that can maintain the load balancing and provide improved strategies through efficient job scheduling that would decrease the average response time and increase the availability of more VMs to allocate new jobs from requesting nodes.

Typically, the previous load balancing methods for Flume which completely depends on the user-specified threshold does not adaptively deal with the performance change of the entire log processing system at runtime. Furthermore, their task-transferring algorithm aggravates the performance degradation of the overloaded node because the excessive data transfer to another node should be done on the overloaded node. In this paper, we propose a new load balancing method for Apache Flume by automatically and dynamically modifying threshold of node load status in accordance with the runtime performance of the system. This feature can be realized by monitoring both the increasing rate of incoming log information in the queue of each collector agent and its occupancy rate at the request of the overloaded or under-loaded collection node in a decentralized manner. The proposed method considerably alleviates the additional overhead incurred by the task migration and makes the load of the entire system as fair as possible by selecting the optimal task migration destination depending on the current load-state values of collector agents unlike the previous round-robin and random ones.

Load balancing is an important part of grid scheduling systems which aims to utilize dynamic and decentralized grid resources without any overcapacity happening at any resources. Load balancing is being considered as an important phase for distributed computing environments. In large scale distributed systems such as grid/cloud computing, it is necessary to use a distributed load balancing system in job scheduling system. Distributed load balancing was identified as a major concern to allow grid computing to scale up the job scheduling. Many algorithms had been proposed for finding the solution of load balancing problem in these fields. But very few algorithms are proposed for distributed load balancing in grid computing environments. In this paper, we have developed an adaptable artificial bee colony (ABC) algorithm for dynamic dividing and scheduling jobs via decentralized schedulers. The proposed method significantly enhances the load balance on the resources. Besides, this method does not need primary information about the capacity and power of the resources which is compatible with the variable and heterogeneous nature of decentralized scheduling. The proposed method is compared with the cuckoo based scheduling algorithm and OSL decentralized scheduling method. The results of the simulations revealed that the proposed method is significantly better than the OSL method. It also outperforms the cuckoo based scheduling algorithm in most of simulations.

Nowadays, different types of bandwidth eater are growing rapidly. Cloud computing as an Internet computing has propagate day by day to provide different type of accommodations and resources to web utilizer. Cloud computing employs Internet resources to execute sizably voluminous-scale tasks. Ergo, to cull felicitous node to execute a task is able to enhance the performance of astronomically immense-scale cloud computing environment. There are several different nodes in a cloud computing system. Namely, each node has different capability to execute task; hence, only consider the CPU remaining of the node is not enough when a node is opted to execute a task. Consequently, how to select an efficient node to execute a task is very consequential in a cloud computing.In this paper, we propose a scheduling algorithm, Load Balancing through Arranging Task with Completion Time, LBATCT which combines minimum completion time and load balancing strategies. For the case study, LBATCT can provide efficient utilization of computing resources and maintain the load balancing in cloud computing environment.

Load balancing of virtual machines is one of the most significant issues in cloud computing research. A common approach is to employ intelligent algorithms such as Ant Colony Optimization (ACO). However, there are two main issues with traditional ACO. First, ACO is very dependent on the initial conditions, which might affect the final optimal solution and the convergence speed. To solve this problem, we propose to employ Genetic Algorithm (GA) for ACO initialization. Second, ACO could arrive at local optimal point, and the convergence speed is typically low. Along this line, we introduce the idea of Simulated Annealing (SA) to avoid local optimal and accelerate the convergence. Lastly, our experiments show that our improved ACO achieves good performance in load balancing.

In order to reduce business latency and packet loss rate, to improve the throughput of integration of heterogeneous wireless network, to achieve load diversification and to improve end quality of service, while there are many problems on the dropout rate of the traditional load balancing algorithm in processing throughput, delay and business, therefore, gateway load balancing algorithm is proposed in this paper. All terminals in the access network can reflect the effectiveness of the average network load level of the network, this algorithm will gain weight of the load in the network of small business terminal to switch to the network load which is light. First, it defines the heterogeneous networks and network terminal payoff function utility function, which are used to characterize the experience and network QOS terminal load situation, and then presents the specific processes of the gateway load balancing algorithm. Finally, switching decisional load balancing algorithm, proposed by Yan X, etc. is compared with simulation experiments and it shows that: the proposed gateway load balancing algorithm has strong robustness to achieve network load balancing and to achieve a balanced use of network resource.

With rapidly growing influence and demand for cloud computing services, issues involving control, migration, security, availability of data, trust matters directly related to sensitive information stored can no longer be treated lightly. Through our work as explained in this paper, we discuss these topics, and also review several algorithms which are used in cloud computing. These algorithms are implemented in a cloud computing architecture to balance load to improve efficiency. Weighted active monitoring load balancing algorithm, dynamic load balancing algorithm, static algorithms, and ant colony algorithm are all used for load balancing in distributed computing systems. In this paper, we propose a load balancing technique based on Tree Parity Machine. Our approach is to design a Tree Parity Machine based model that would distribute workload evenly among all nodes. The technique proposed by us is not complicated. It has been conceived such that it can work efficiently with training sets that have been proven to produce intended results. Our Tree Parity Machine based model would predict the demand and, accordingly, allocate necessary resources. Thus, it would be able to maintain active servers to meet existing demands. As a result, consumption of energy can be significantly lowered. The conservative approach of over-provisioning is, thus, avoided.

With Hadoop been widely used, job scheduling technology, as a key technology in Hadoop, has been developed rapidly. However, Hadoop's default scheduling algorithm Fair Scheduler when performing the task scheduler does not consider load balancing status of each node cluster system, leading to low efficiency great job. For defect fair share scheduling algorithm, and combined LATE scheduling algorithm, load balancing scheduling algorithm based on a fair share. Experimental results show that the fair share scheduling algorithm can be improved in the scheduling task when taking into account the situation of each node load balancing, improve the efficiency of large jobs.

Mobility load balancing (MLB) is a significant technology in Long Term Evolution Advanced heterogeneous cellular networks (HCN). To solve high handover performance loss issue and the potential Ping-Pong problem, a novel MLB scheme based on cell priority is proposed. Considering the impact of different user mobile speeds and cell coverage radius of HCN, we define a handover tolerance as the priority of load balancing to reduce the system performance loss caused by user handover. Furthermore, we use the load balancing index to evaluate the load balancing of HCN, then the load allocation mechanism of overlapping cells is deployed to overcome potential Ping-Pong problem. Simulation results show that the proposed MLB scheme has better performance than the original MLB scheme in terms of the system throughput and the number of unsatisfied users. Meanwhile, the handover times are also improved.