Distributed Utilization Control for Real-Time Clusters with Load Balancing

We describe an admission control and load balancing scheme for multicomputer World Wide Web servers. The scheme consists of a frontend admission control function which regulates requests sent to backend Web server using periodic load measurements passed from the backends to the frontends. The aims of scheme are two-fold: to ensure that traffic offered to backends can be serviced promptly, and to make full use of the backend capacity. We describe simulation results and an Erlang based implementation of the scheme. It is shown that the algorithm is trivial to implement, has negligible computational complexity, and provides effective load balancing and control. The scheme has now been implemented in the Eddie open source project, an Ericsson sponsored effort aimed at delivering commercial grade, quality of service driven Web server solutions.

Distributed multimedia applications (DMA), such as video-on-demand (VoD) require dynamic quality-of-service (QoS) guarantee from end-user machines for their continuous multimedia streams. The QoS requirements and improvement in job execution time can be achieved with the aid of proper load balancing among the machines. An effective way to achieve load balance is to link up these end-user machines with multiple potential heterogeneous idle or under-loaded clustered-servers and allow these servers with idle retrieval bandwidth to help out end-user machines that are low power or temporarily overloaded (bottleneck). The clustered VoD servers approach provides scalability and availability compared to a single video server. In this paper we design and implement a new clustered-server-client architecture for multimedia VoD applications along with a new REMS+VoD algorithm. Rigorous simulation for the algorithm has been performed by varying both the number of video-requests (sessions) and the number of potential servers. The simulation results show that our approach provides: (1) effective load balancing; (2) scalability; and (3) availability in a VoD system

Hybrid grey wolf and improved particle swarm optimization with adaptive intertial weight-based multi-dimensional learning strategy for load balancing in cloud environments

With the explosive growth of the Internet of Things (IoT), an increasing amount of sensor data generated by soft real-time IoT applications has been moved to data centers for storage and data analysis. Large amounts of these data are required to be processed within a given deadline to ensure application performance. Therefore, meeting the transmission deadlines of data flows for soft real-time applications has always been crucial yet challenging to current data centers. Recent progress has demonstrated that adopting parallel data transmission over multipath data center network combining with effective load balancing can achieve a high bisection network bandwidth, thus speeding up the network transfer of data flows. Nevertheless, the deadline miss ratios (DMRs) of these flows are not lowered as expected since the existing load balancing schemes are naturally agnostic to the deadline requirement. They are either unable to reroute traffic flexibly or aimlessly reroute these deadline-restrained flows, regardless of their urgent levels and path conditions. To address these inefficiencies, we propose a deadline-aware load-balancing scheme, namely, DLB, which perceives the deadline requirements and helps the urgent flows to timely switch to those faster transmission paths to complete quickly. Specifically, DLB computes the urgent level for each flow in real time to judge if the switch needs to make proactive rerouting. When a flow is nonurgent, DLB does not proactively change its transmission path, leaving more available paths to those flows with higher urgent levels. When a flow becomes extremely urgent, it immediately switches to those light-loaded paths to finish its data transmission before its deadline as far as possible. Experimental results of NS2 simulations and real testbed implementations show that DLB reduces the DMRs by up to 50% compared to the state-of-the-art data center load-balancing schemes, while only induces trivial overhead during deployment.

Traditional load balancer has no flexibility to manage growing network traffic in real time and is expensive too. Software-defined networking (SDN) is a promising solution for handling today’s growing network architecture. To address issues such as network congestion and overloading, service providers use multiple replicas in the server cluster to provide the same services where network virtualization and effective load balancing is very important. This work proposes the implementation of real-time traffic management strategy that distributes the network requests among multiple servers based on a fuzzy logic. The fuzzy membership characteristic that affects the performance parameters of server load has been analyzed, and load state of virtual servers in real-time is evaluated through fuzzy logic. Considering major parameters of Web server (CPU, RAM and bandwidth utilization) as an input of fuzzy system, the clients requests are forwarded to the server having minimum load at real time. The proposed load balance algorithm written in Python is simulated on Mininet, and performance of each Web servers is compared with existing round robbin (RR) and least connections (LC) load balancing schemes. The results demonstrate that the proposed scheme has improved response time and higher throughput as compared to the other load balance solutions.KeywordsSoftware-defined networkingOpenFlowLoad balancerServer cluster

With the rapid development of processing and storage technologies and the success of the Internet, computing resources have become cheaper, more powerful and more ubiquitously available than ever before. This technological trend has enabled the realization of a new computing model, called cloud computing. In cloud, scheduling is an important application. In cloud environments, load balancing task scheduling is an important problem that directly affects resource utilization. Undoubtedly, load balancing scheduling is a serious aspect that should be considered because of its significant impact on both the back end and the front end of the cloud research industry. Good resource utilization is achieved whenever an effective load balance is achieved in the cloud. But, load balancing in cloud computing is an NP-hard optimization problem. In order to accomplish this problem, a novel load balancing task scheduling algorithm in cloud using Adaptive Dragonfly algorithm (ADA) is proposed. The ADA is a combination of dragonfly algorithm and firefly algorithm. Moreover, to attain the better performance, multi-objective function is developed based on three parameters namely, completion time, processing costs and load. Finally, the performance of proposed methodology is evaluated in terms of different metrics namely, execution cost and execution time. The experimental results demonstrate that a proposed approach accomplishes better load balancing result compared to other approaches.

Effective load balancing is critical in ensuring optimal resource utilization, reducing latency, and improving the overall performance of distributed systems. This report commences with a comprehensive literature review on existing load-balancing algorithms, examining their methodologies, strengths, and limitations within various computing environments, including cloud computing, data centers, and network traffic management. Despite significant advancements in this field, the dynamic nature of distributed systems, coupled with the ever-increasing demand for efficient data processing, poses ongoing challenges. In response, this study proposes a novel load-balancing algorithm to address these contemporary challenges. The approach leverages dynamic and hybrid load balancing, distinguishing it from existing methods. Detailed analysis show that this approach offers improved scalability, response time, and resource allocation efficiency, particularly in scenarios characterized by highly volatile workloads. This report details the conceptual framework of the proposed algorithm and offers a concise understanding of how cloud-based load balancers can be optimized to delegate compute and focus on just routing.

Modern distributed systems increasingly operate across large scale clusters where data and services are accessed through multiple intermediate network components. In such environments, the number of communication hops between clients and target resources has a direct impact on performance, scalability, and network efficiency. Existing distributed architectures commonly rely on static routing, uniform placement, or centralized load balancing strategies that do not explicitly consider hop count during request routing. As cluster size grows, hop count increases steadily, leading to higher transmission overhead, increased processing at intermediate nodes, and inefficient utilization of network paths. The accumulation of additional hops introduces avoidable delays, increases contention on shared network components, and amplifies congestion within the system. Although individual hop delays may appear small, their cumulative effect significantly impacts system efficiency as scale increases. Existing solutions primarily focus on load balancing or throughput improvement while hop count remains an indirect or overlooked factor. This paper addresses the problem of excessive hop count in distributed systems by examining how routing and placement decisions influence communication distance. The study focuses on identifying inefficiencies introduced by static and locality unaware routing strategies and evaluates their impact on hop count as cluster size increases. By analyzing hop count behavior across varying node configurations, the paper highlights how existing designs fail to scale efficiently from a network perspective. The objective is to bring hop count to the forefront as a critical performance metric and to motivate routing and placement strategies that minimize unnecessary communication paths, thereby improving scalability and network efficiency in distributed platforms.

An important mechanism in any distributed object-based system is a means of managing load imbalances. This paper introduces the Bellerophon load balancer. The approach described provides dynamic system-level balancing in a topology independent fashion that is appropriate for avoiding gross imbalances of load. A number of novel techniques are combined with a heuristic to form a hybrid local garbage detector and load balancer. Multiple load measures are regularly compared, by each node with a dynamically varying subset of the others; and clumps of objects, selected to avoid breaking cycles, are transferred to improve the load balancing. >

Firewalls are installed at network perimeters to secure organization's network as alternatives lo general gateways. Because of potential performance problems on the gateways, load balancing technique has been applied. However, compared to general gateways, firewalls require more intelligent load balancing method lo process massive network traffic because of their relatively complex operations. In this paper, we analyze the inherent problems of existing simple load balancing methods for firewalls and propose the interval weighted load balancing (IWLB) to enhance the processing of massive network traffics. The IWLB deals with network traffics in consideration of the characteristics of application protocols to achieve more effective load balancing. We observed that the IWLB outperforms other simple load balancing methods during our simulation. Therefore, we expect that the IWLB is suitable to balancing loads for multiple firewalls at a network perimeter.

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.

In order to solve the communication efficiency and the load balancing of P2P network, a multi-link concurrent P2P communication model is proposed. It introduces concurrent communication mechanism, assigns proper communication task to all nodes according to the communication capability of nodes and the communication weight between nodes, implements the traffic load balancing and shortens communication time. The model has high concurrency, strong robustness, and effective load balancing, so it is suitable for multicast communication and network data mass transmit.

Load balancing in ad hoc networks is more challenging issue than that in wired networks because the nature of decentralized network management and terminal mobility makes it difficult to realize appropriate controls for the whole network. Although some traffic-based load balancing methods that work with rerouting mechanisms have been proposed, they are, due to the overhead for rerouting, hard to adapt the environment where the traffic or the topology changes in a short period. Furthermore, the conventional methods cannot always find appropriate routes since they only give attention to the current transmission route. This paper proposes a load balancing method based on adaptive transmission rate control using neighbouring terminals' status. The proposed method does not adopt a rerouting mechanism but introduce a rate control so that we do not have to consider the overhead for rerouting. Computer simulation showed that, depending on terminals' status, our method achieves more effective load balancing, as well as better throughput, than the conventional rerouting-based methods.

Cloud computing consists of a cluster of computing resources that are delivered over a network, which is accomplished by utilizing virtualization technologies to consolidate and allocate resources suitable for various different software applications. Therefore, an efficient task scheduling in the cloud would be required to improve the performance of the cloud. In this paper, implementation of a model that seeks to improve load balancing algorithm for virtual machine load balancing was performed using simulations. A method by which average burst time was used as the time quantum for the round robin load balancing algorithm to achieve more effective time sharing. Results obtained from the simulations along with performance evaluation carried out shows response time and data center processing time achieved using the improved model is slightly minimal compared to the other algorithms. This shows more effective load balancing by achieving a better overall throughput.

The current database market is fairly evenly split between shared nothing and data sharing systems. While shared nothing systems are easier to build and scale, data sharing systems have advantages in load balancing. In this paper we explore adding data sharing functionality as an extension to a shared nothing database system. Our approach isolates the data sharing functionality from the rest of the system and relies on well-studied, robust techniques to provide the data sharing extension. This reduces the difficulty in providing data sharing functionality, yet provides much of the flexibility of a data sharing system. We present the design and implementation of Chimera -- a hybrid database system, targeted at load balancing for many workloads, and scale-out for read-mostly workloads. The results of our experiments demonstrate that we can achieve almost linear scalability and effective load balancing with less than 2% overhead during normal operation.