Server Load Balancing Analysis for Client Task Assignment in Distributed Systems

In Cloud Computing (CC) environment, load balancing refers to the process of optimizing resources of virtual machines. Load balancing in the CC environment is one of the analytical approaches utilized to ensure indistinguishable workload distribution and effective utilization of resources. This is because only by ensuring effective balance of dynamic workload results in higher user satisfaction and optimal allocation of resource, therefore improve cloud application performance. Moreover, a paramount objective of load balancing is task scheduling because surges in the number of clients utilizing cloud lead to inappropriate job scheduling. Hence, issues encircling task scheduling has to be addressed. In this work a method called, Ford Fulkerson and Newey West Regression-based Dynamic Load Balancing (FF-NWRDLB) in CC environment is proposed. The FF-NWRDLB method is split into two sections, namely, task scheduling and dynamic load balancing. First, Ford Fulkerson-based Task Scheduling is applied to the cloud user requested tasks obtained from Personal Cloud Dataset. Here, employing Ford Fulkerson function based on the flow of tasks, energy-efficient task scheduling is ensured. The execution of asymmetrical scientific applications can be smoothly influenced by an unbalanced workload distribution between computing resources. In this context load balancing signifies as one of the most significant solution to enhance utilization of resources. However, selecting the best accomplishing load balancing technique is not an insignificant piece of work. For example, selecting a load balancing model does not work in circumstances with dynamic behavior. In this context, a machine learning technique called, Newey West Regression-based dynamic load balancer is designed to balance the load in a dynamic manner at run time, therefore ensuring accurate data communication. The FF-NWRDLB method has been compared to recent algorithms that use the markov optimization and the prediction scheme to achieve load balancing. Our experimental results show that our proposed FF-NWRDLB method outperforms other state of the art schemes in terms of energy consumption, throughput, delay, bandwidth and task scheduling efficiency in CC environment.

This paper developes a design to Windows operating system for basic platform series, in multiple servers distributed network formed by the environment of the realization of the instant communication system. That is based on TCP/IP protocol, multiple clients, a load server, and more data servers constitute a distributed network. System information communication hub, connected to all the clients and the servers, to communication contents and directional forward receiving, and at the same time, supervises each server load condition and balance system performance. The work bench of network Socket, multithreading asynchronous callback technology under the network platform is adopted in this paper.

With the development of high‐performance computing, it is possible to solve large‐scale computing problems. However, the irregularity and access characteristics of computing problems bring challenges to the realisation and performance optimisation. Improving the performance of a single core makes it challenging to maintain Moore's law, and multi‐core processors emerge. A chip brings together multiple universal processor cores of equal status and has the same structure supported by an isomorphic multi‐core processor. In high‐performance computing, the granularity of computing tasks leads to the complexity of scheduling strategies. Satisfying high system performance, load balancing and processor fault tolerance at a minimum cost is the key to task scheduling in the high‐performance field, especially in specific multi‐core hardware architecture. In this study, global real‐time task scheduling is implemented in a high‐performance multi‐core system. The system adopts the hybrid scheduling among clusters and the intelligent fitting within clusters to implement the global real‐time task scheduling strategy. In the cluster scheduling policy, tasks are allowed to preempt the core with low priority, and the priority of tasks that access memory is dynamically improved, higher than that of all the tasks without memory access. An intelligent fitting method is also proposed. When the data read by the task is in the cache and the cache access ability value of the task is within a reasonable threshold, the priority of the task is promoted to the highest priority, preempting the core without the access memory task. The results show that the intelligently fitting global scheduling strategy for multi‐core systems has better performance in the nuclear utilisation rate and task schedulability.

Load balancing and task partitioning are important components of distributed computing. The optimum performance from the distributed computing system is achieved by using effective scheduling and load balancing strategy. Researchers have well explored CPU, memory, and I/O-intensive tasks scheduling, and load balancing techniques. But one of the main obstacles of the load balancing technique leads to the ignorance of applications having a mixed nature of tasks. This is because load balancing strategies developed for one kind of job nature are not effective for the other kind of job nature. We have proposed a load balancing scheme in this paper, which is known as Mixed Task Load Balancing (MTLB) for Cluster of Workstation (CW) systems. In our proposed MTLB strategy, pre-tasks are assigned to each worker by the master to eliminate the worker's idle time. A main feature of MTLB strategy is to eradicate the inevitable selection of workers. Furthermore, the proposed MTLB strategy employs Three Resources Consideration (TRC) for load balancing (CPU, Memory, and I/O). The proposed MTLB strategy has removed the overheads of previously proposed strategies. The measured results show that MTLB strategy has a significant improvement in performance.

Heterogeneous Distributed Computing (HDC) system consists of Workstations (WSs) and Personal Computers (PCs). In HDC system, each WS/PC may have different processor and performance. In order to take advantage of this diversity of processing power of a system, an effective task partitioning, scheduling, and load balancing are needed to get the optimum performance. This paper examines the effectiveness of task partitioning and scheduling strategies for image (raytracing) processing application on HDC system. The static and dynamic/Run-time Task Scheduling (RTS) strategies are shown inadequate for balancing the load of HDC system. Two adaptive tasks scheduling strategies are proposed for HDC image computing system. These adaptive strategies are: i) Master Initiate Sub-task size (MIS) strategy (based on centralized resources management approach), and ii) Worker Initiated Sub-task size (WIS) strategy (based on semi-decentralized resources management approach). The measured results show that the adaptive (MIS & WIS) strategies dramatically improve the performance of HDC raytracing system and remedy the defects of static and RTS strategies. Performances of the all investigated strategies are evaluated on manager/master and workers model of HDC system. In performance comparisons of MIS and WIS strategies, the WIS strategy shows a slightly better speedup and scalability over MIS strategy.

This paper studies cluster load balancing policies and system support for fine-grain network services. Load balancing on a cluster of machines has been studied extensively in the literature, mainly focusing on coarse-grain distributed computation. Fine-grain services introduce additional challenges because system states fluctuate rapidly,for those services and system performance is highly sensitive to various overhead. The main contribution of our work is to identify effective load balancing schemes for fine-grain services through simulations and empirical evaluations on synthetic workload and real traces. Another contribution is the design and implementation of a load balancing system in a Linux cluster that strikes a balance between acquiring enough load information and minimizing system overhead. Our study concludes that: 1) Random polling based load-balancing policies are well-suited for fine-grain network services: 2) A small poll size provides sufficient information for load balancing, while an excessively large poll size may in fact degrade the performance clue to polling overhead; 3) Discarding slow-responding polls can further improve system performance.

Most of the existing solutions on task scheduling and resource management in grid computing are based on the traditional client/server model, enforcing a homogeneous policy on making decisions and limiting the flexibility, unpredictable reliability and scalability of the system. Thus, we need a well organised system architecture to provide high system availability with resource scheduling scheme for grid environment. In this paper, we integrate grid with P2P on to the hypercube topology with additional neighbourhood links for task scheduling and load balancing, which gives better makespan and balances the load. We propose the SPA-based task scheduling methodology in order to enhance system performance in hypercubic P2P grid (HPGRID). The simulation results show that the SPA-based min-mean scheduling minimises the makespan along with load balancing and guarantees the high system availability in system performance. At last, the min-mean algorithm is compared with min-min and max-min algorithm using SPA, by simulate experimentation, and it shows that the new algorithm has a better quality of system load balancing and the utilisation of system resources.

Multiplayer online games are on the rise with millions of registered player and hundreds of thousands concurrent players. Current state of the art servers achieve scalability by splitting the game world into linked mini worlds that can be hosted on separate servers. One of the problems is that, players are flocking to one area, resulting in an overloaded server with decreasing Quality of Service(QoS) for the players. A number of approaches were developed to address these issues, by balancing loads between the over-loaded and under-loaded servers. This paper investigates a new dimension that is created due to the load balancing of servers. Load balancing among servers is sensitive to correct status information. The Markov based load prediction was introduced in this paper to predict load of under-loaded servers, based on arrival μ and departure λ rates of players. The prediction based algorithm is proposed to minimize the effect of out dated status information. This approach was compared with normal load status information exchange algorithm. The model presented in this paper does not deal directly with optimizing the load balancing of the server but rather tries to present a new insight that need to be considered when developing load balancing algorithm, that is the reliability of the information that is shared. Simulation results show that Markov based prediction of load information performed better from the normal load status information sharing.

The global optimal Web service selection based on quality of service (QoS) in cloud environment has become a research focus when there are lots of the same or similar services. In this environment, it is possible that many service users request the same or similar services at the same time, which will result in users' unsatisfied requirement and services' load imbalance. The existing service selection approaches usually suppose that service's load capacity is infinite and user always select the service with the best expected QoS despite the amount of user requests. Therefore, it is very important problem how to get a tradeoff between the users' satisfied requirement and service load balance. To solve this problem, this paper presents a global optimal service selection approach based on QoS and load-aware in cloud environment. In this approach, we first build a user QoS utility model which describes the relationship between user's request and services' QoS, and design a service's load capacity model to achieve the load capacity of a service. Then, we use 0-1 integer programming to build a global optimal model based on QoS utility of users and services' load capacity, and provide the optimal service selection algorithm for users. Finally, by conducting large-scale experiments based on a Web service dataset, we show that our approach can effectively help users to select high qualified services while keeping load balance of services in cloud environment.

Tasks scheduling problem is a key factor for a distributed system in order to achieve better efficiency. The problem of tasks scheduling in a distributed system can be stated as allocating tasks to processor of each computer. The objective of this problem is minimizing Makespan and communication cost while maximizing CPU utilization. Scheduling problem is known as NP-complete. Hence, many genetic algorithms have been proposed to search optimal solutions from entire solution space. However, the existing approaches are going to scan the entire solution space without consideration to techniques that can reduce the complexity of the optimization. In other words, the main weakness of these methods is to spend much time doing scheduling and hence need to exhaustive time. In this paper we use Learning algorithm to cope with the weakness of GA based method. In fact we use the Learning automata as local search in the memetic algorithm. Experimental results prove that the proposed method outperforms the existent GA based method in terms of communication cost, CPU utilization and Makespan.

In this paper, we classify the dynamic, decentralized load balancing algorithms for heterogenous distributed computer systems into three policies: queue adjustment policy (QAP), rate adjustment policy (RAP) and queue and rate adjustment policy (QRAP). We propose two efficient algorithms, referred to as rate based load balancing via virtual routing (RLBVR) and queue based load balancing via virtual routing (QLBVR), which belong to the above RAP and QRAP policies, respectively. We also consider algorithms estimated load information scheduling algorithm (ELISA) that was introduced in the literature, to implement QAP policy. Our focus is to analyze and understand the behaviors of these algorithms in terms of their load balancing ability under varying load conditions (light, moderate, or high) and the minimization of mean response time of jobs. We compare the above classes of algorithms by a number of rigorous simulation experiments to elicit their behavior under some influencing parameters. From these experiments, recommendations are drawn to prescribe the suitability of the algorithms under various situations.

For the problem of resource load unevenness of task scheduling in cloud computing, this paper proposes Load Balancing Ant Colony Optimization (LBACO) based on load conditions of virtual machines. At the same time, the pheromone initialization, heuristic function, state transition probability, and pheromone updating method in the ant colony algorithm(ACO) are improved. The improved scheduling strategy was experimented on the CloudSim platform. The experimental results show that compared with ACO and RR algorithms, the LBACO algorithm achieves better performance in terms of makespan of task sets and the system load balance.

A distributed system consists of several autonomous nodes. In a distributed system some of the nodes may be overloaded due to a large number of job arrivals while other nodes may remain idle without any processing. The performance of a distributed system depends crucially on dividing up work effectively among the computing nodes. So a way is needed to share load across all the computing nodes. In centralized load balancing schemes, the load balancing decision is taken by a central server. So this scheme is not scalable. In contrast, fully distributed schemes are scalable, but they use local information. A hierarchical dynamic load balancing model is proposed in this paper where an ordinary node does not need to have a global system wide knowledge about the states of other nodes in the system. The proposed model is semi distributed as each cluster is represented by a cluster master.

Cloud computing (CC) emerged as one of the important utility such as water and electricity bills, where the user has to pay for whatever quantity they have utilized for their tasks. As cloud users are increasing; so the crucial challenges for the cloud service provider (CSP) is to balance the load among the resources shared by the end-users and curb increased security risks, misuse, or malicious attacks in cloud computing. The functionality of load balancing is divided into two functions, first, there will be allocation of resources and the second is the provisioning of resources along with task scheduling in the distributed system such as CC. Although many state-of-the-art approaches are available in the literature which provides load balancing and better resource utilization. In this paper, we build a dynamic prediction approach for cloud resource usage, discuss a load balancing technique, and identify sudden spikes and failures that are causes of the anomaly using a reactive and proactive approach. The final result demonstrates a comparative analysis of deep learning models for the prediction of cloud resource utilization, insight into dynamic load balancing technique and anomaly detection.KeywordsAnomaly detectionCloud computingCloud service providerDeep learningLoad balancingOutliers

Graph computing plays an important role in mining data at large scale. Partition is the primary step when we process large graph in a distributed system. A good partition has less communication and memory cost as well as more balanced load to take advantage of the whole system. Traditional edge cut methods introduce large communication cost for realistic power law graphs. Current vertex cut methods perform poorly with little consideration on load balance especially for online streaming vertex cut partition. In this paper, we formulate the total cost (partition cost, communication cost and computing cost) of graph computing especially that in iterating algorithms and analyze the cost of current partitioning methods. In addition, we explore a novel vertex cut method to ensure lower total cost. It has more balanced load with fewer communications. Experiments show that our method outperforms in state of the art graph computing frameworks at an average of 10 percent.