Load Balancing Problem Research Articles

A systematic literature review for load balancing and task scheduling techniques in cloud computing

Cloud computing is an emerging technology composed of several key components that work together to create a seamless network of interconnected devices. These interconnected devices, such as sensors, routers, smartphones, and smart appliances, are the foundation of the Internet of Everything (IoE). Huge volumes of data generated by IoE devices are processed and accumulated in the cloud, allowing for real-time analysis and insights. As a result, there is a dire need for load-balancing and task-scheduling techniques in cloud computing. The primary objective of these techniques is to divide the workload evenly across all available resources and handle other issues like reducing execution time and response time, increasing throughput and fault detection. This systematic literature review (SLR) aims to analyze various technologies comprising optimization and machine learning algorithms used for load balancing and task-scheduling problems in a cloud computing environment. To analyze the load-balancing patterns and task-scheduling techniques, we opted for a representative set of 63 research articles written in English from 2014 to 2024 that has been selected using suitable exclusion-inclusion criteria. The SLR aims to minimize bias and increase objectivity by designing research questions about the topic. We have focused on the technologies used, the merits-demerits of diverse technologies, gaps within the research, insights into tools, forthcoming opportunities, performance metrics, and an in-depth investigation into ML-based optimization techniques.

The optimization problem of system load balancing and its solution for industrial Internet-of-Things data management

The optimization problem of system load balancing and its solution for industrial Internet-of-Things data management

Quadratic functions for efficient load balancing in the terminals of a substation of a three-phase asymmetric network with power loss reduction capabilities

This research addresses the problem of optimal load balancing in terminals of the three-phase substation by proposing three quadratic objective functions. These objective functions are formulated considering active, reactive, and apparent power consumptions aggregated at the terminals of the substation. The proposed formulation belongs to the mixed-integer quadratic models’ family, which can be solved globally with specialized mixed-integer convex tools. To evaluate the effect of load redistribution in the substation terminals, the 15- and 35-bus grids are tested using each of the proposed quadratic functions. In addition, Broyden's unbalanced power flow method is used to determine the extent of power loss reduction and enhancement of voltage profile. Numerical results confirm the effectiveness of the proposed mixed-integer quadratic model in enhancing electrical performance in three-phase asymmetric networks through load balancing at the substation terminals. After solving each quadratic function for the 15-bus grid, power losses were reduced between 12.9624% and 17.2550%, and these reductions were between 5.0771% and 7.7389% in the 35-bus grid.

PA-SPS: A predictive adaptive approach for an elastic stream processing system

Stream Processing Systems (SPSs) dynamically process input events. Since the input is usually not a constant flow, presenting rate fluctuations, many works in the literature propose to dynamically replicate SPS operators, aiming at reducing the processing bottleneck induced by such fluctuations. However, these SPSs do not consider the problem of load balancing of the replicas or the cost involved in reconfiguring the system whenever the number of replicas changes. We present in this paper a predictive model which, based on input rate variation, execution time of operators, and queued events, dynamically defines the necessary current number of replicas of each operator. A predictor, composed of different models (i.e., mathematical and Machine Learning ones), predicts the input rate. We also propose a Storm-based SPS, named PA-SPS, which uses such a predictive model, not requiring reboot reconfiguration when the number of operators replica change. PA-SPS also implements a load balancer that distributes incoming events evenly among replicas of an operator. We have conducted experiments on Google Cloud Platform (GCP) for evaluation PA-SPS using real traffic traces of different applications and also compared it with Storm and other existing SPSs.

Hybrid Agent-Based Load-Balancing Approach Used in an IaaS Platform

Cloud computing has received a resounding welcome. It was created following methodical and thorough study in web services, distributed computing, utility computing, and virtualization, and it offers several benefits, including lower costs, less space required, and easier management. These advantages bring in a significant number of new users to the cloud platform every day. In addition, because cloud computing is an Internet-based computing paradigm, it must deal with the issue of overwhelming demands through effective load-balancing. A very small number of studies only focus on load-balancing problems in cloud computing platforms, while the majority of load-balancing research is accessible in many domains, including parallel, distributed, and grid computing. Infrastructure as a Service (IaaS), Software as a Service, and Platform as a Service are the three basic categories under which cloud computing falls. For these models, there are notable differences in the load-balancing techniques used. This work compared the outcome with the current method and presented a hybrid agent-based load-balancing approach for the IaaS platform.

An intelligent load balancing algorithm for 5G‐satellite networks

SummaryCellular networks are projected to deal with an immense rise in data traffic, as well as an enormous and diverse device, plus advanced use cases, in the nearest future; hence, future 5G networks are being developed to consist of not only 5G but also different radio access technologies (RATs) integrated. In addition to 5G, the user's device (UD) will be able to connect to the network via LTE, WiMAX, WiFi, Satellite and other technologies. On the other hand, Satellite has been suggested as a preferred network to support 5G use cases. However, achieving load balancing is essential to guarantee an equal amount of traffic distributed between different RATs in a heterogeneous wireless network; this would enable optimal utilisation of the radio resources and lower the likelihood of call blocking/dropping. This study presented an artificial intelligent‐based application in heterogeneous wireless networks and proposed an enhanced particle optimisation (EPSO) algorithm to solve the load balancing problem in 5G‐Satellite networks. The algorithm uses a call admission control strategy to admit users into the network to ensure that users are evenly distributed on the network. The proposed algorithm was compared with the Artificial Bee Colony and Simulated Annealing algorithm using three performance metrics: throughput, call blocking and fairness. Finally, based on the experimental findings, results outcomes were analysed and discussed.

Load balancing and topology dynamic adjustment strategy for power information system network: a deep reinforcement learning-based approach

As power information systems play an increasingly critical role in modern society, higher requirements are placed on the performance and reliability of their network infrastructure. In order to cope with the growing data traffic and network attack threats in the power information system, we select the power information system data center network as the research object and design an overall system solution based on software defined network, including the application layer, control layer and infrastructure layer. A typical fat tree network topology is simulated and analyzed. We define the load balancing and network topology dynamic adjustment problem as a Markov decision process, and design a data flow path acquisition method based on breadth-first search to construct the action space of each host. Then, a deep reinforcement learning algorithm based on deep Q-network, priority experience replay and target network is introduced to provide solutions for optimizing the performance of power information systems and responding to network attacks. Simulation results show that the proposed method is better than the traditional equal-cost multi-path algorithm in terms of average bandwidth utilization, average jitter and average packet loss, and can reduce the probability of network nodes being attacked by more than 11%.

Load balancing model for cloud environment using swarm intelligence technique

A distributed system with a shared resource pool offers cloud computing services. According to the provider’s policy, customers can enjoy continuous access to these resources. Every time a job is transferred to the cloud to be carried out, the environment must be appropriately planned. A sufficient number of virtual machines (VM) must be accessible on the backend to do this. As a result, the scheduling method determines how well the system functions. An intelligent scheduling algorithm distributes the jobs among all VMs to balance the overall workload. This problem falls into the category of NP-Hard problems and is regarded as a load balancing problem. With spider monkey optimization, we have implemented a fresh strategy for more dependable and efficient load balancing in cloud environments. The suggested optimization strategy aims to boost performance by choosing the least-loaded VM to distribute the workloads. The simulation results clearly show that the proposed algorithm performs better regarding load balancing, reaction time, make span and resource utilization. The experimental results outperform the available approaches.

An adaptive load balancing strategy for stateful join operator in skewed data stream environments

As one of the most computationally intensive operations in stream processing applications, join operation can cause severe load imbalance problem when dealing with skewed data. Most of the popular solutions focused on monitoring-based dynamic balancing strategies, making it difficult to quickly adapt to the changing frequency of data stream, and sometimes failing the balancing strategies that try to address the skewed load in the cluster. To address these issues, we propose to use the prediction results of a deep reinforcement learning model and adjust the grouping strategy in advance before the frequency change of data stream. It will enable the system to quickly adapt to data stream fluctuation, while managing the resources for effective resource utilization. The following contributions are made in this paper: 1) Explore the main factors that trigger the load skewness problem in distributed stream join systems and carefully model the load balancing problem at the application level. 2) Develop a Gated Recurrent Unit Sequence to Sequence model to predict key frequency distribution of streams, and propose a dynamic grouping algorithm and a feedback-based resource elasticity scaling algorithm to solve the load imbalance problem caused by hot keys in real time. 3) Design and implement an adaptive stream join system Aj-Stream based on the prediction model and the proposed algorithm on Apache Storm. 4) Evaluate the system performance through extensive experiments on a large scale real-world dataset and multiple synthetic datasets. The experimental results demonstrate that the Aj-Stream proposed in this paper exhibits stable throughput and latency performance with both static data streams of varying skewnesses and dynamic data streams. In comparison to existing stream-connected systems, Aj-Stream demonstrated a 22.1% increase in system throughput and a 45.5% decrease in system latency when dealing with frequently fluctuating data streams.

Hybridized Darts Game with Beluga Whale Optimization Strategy for Efficient Task Scheduling with Optimal Load Balancing in Cloud Computing

A cloud computing technology permits clients to use hardware and software technology virtually on a subscription basis. The task scheduling process is planned to effectively minimize implementation time and cost while simultaneously increasing resource utilization, and it is one of the most common problems in cloud computing systems. The Nondeterministic Polynomial (NP)-hard optimization problem occurs due to limitations like an insufficient make-span, excessive resource utilization, low implementation costs, and immediate response for scheduling. The task allocation is NP-hard because of the increase in the amount of combinations and computing resources. In this work, a hybrid heuristic optimization technique with load balancing is implemented for optimal task scheduling to increase the performance of service providers in the cloud infrastructure. Thus, the issues that occur in the scheduling process is greatly reduced. The load balancing problem is effectively solved with the help of the proposed task scheduling scheme. The allocation of tasks to the machines based on the workload is done with the help of the proposed Hybridized Darts Game-Based Beluga Whale Optimization Algorithm (HDG-BWOA). The objective functions like higher Cloud Data Center (CDC) resource consumption, increased task assurance ratio, minimized mean reaction time, and reduced energy utilization are considered while allocating the tasks to the virtual machines. This task scheduling approach ensures flexibility among virtual machines, preventing them from overloading or underloading. Also, using this technique, more tasks is efficiently completed within the deadline. The efficacy of the offered arrangement is ensured with the conventional heuristic-based task scheduling approaches in accordance with various evaluation measures.

Graph based routing algorithm for torus topology and its evaluation for the Angara interconnect

Several approaches and techniques exist to resolve load balancing problem in general and torus topology networks. Graph methods are natural ways to perform balancing of routing paths. A routing balancing algorithm must operate within the constraints of the underlying network architecture that limits several parameters, such as the number of logical paths in the network. In this paper, we consider a torus topology that is one of the common topologies that are used in high performance computing systems. We introduce a routing graph that corresponds to a interconnect topology, abstracts interconnect routing rules, providing one-to-one correspondence of network routes and graph paths. We propose a deadlock-free routing algorithm based on a fast single-source shortest path algorithm in a routing graph for the deterministic routing of a torus topology interconnect with a single virtual channel. The proposed algorithm is a tradeoff between two existing routing algorithms, also the algorithm is optimized for multidimensional torus topology and can be applied to any torus topology HPC system. We present a complete description of a routing graph that abstracts the Angara interconnect with 4D torus topology. We evaluated the proposed routing algorithm and benchmarked the maximum performance improvement of 71% for the Alltoall pattern for torus topology systems up to 432 nodes on the Angara interconnect simulator. The performance improvement of more than 5% was obtained for the NPB FT and IS application kernels on a 32-node supercomputer.

Online cardinality constrained scheduling

In online load balancing problems, jobs arrive over a list. Upon arrival of a job, the algorithm is required to assign it immediately and irrevocably to a machine. We consider such a makespan minimization problem with an additional cardinality constraint, i.e., at most k jobs may be assigned to each machine, where k is a parameter of the problem. We present both upper and lower bounds on the competitive ratio of online algorithms for this problem with identical machines.

Joint optimization of resource allocation and computation offloading based on game coalition in C-V2X

In order to solve the problem of limited resources in the vehicle, mobile edge computing (MEC) is integrated into the cellular-vehicle-to-everything (C-V2X) system to provide users with low-latency services. Considering the resource limitation of computing, storage and communication of MEC servers, it is necessary to improve the system performance through the collaborative optimization of multi-domain resources. Therefore, for applications with double dependence on time and data in C-V2X scenarios, we design a MEC hierarchical resource management framework to jointly optimize system offloading decision, scheduling decision, and caching decision to minimize the system delay. The optimization problem is decomposed into a resource allocation problem within a single MEC server and a load balancing problem among multiple MEC servers. For the former, we present a task scheduling algorithm based on the latest start time and a caching decision algorithm based on dynamic programming to minimize the average task completion delay; for the latter, we present a load balancing algorithm based on the coalition game to minimize the global system delay. Simulation results show that the proposed scheme can significantly improve the performance in terms of application completion delay, application failure rate and resource utilization compared with the benchmark schemes.

Best Effort Workload Disparity Minimization in Multi-Agent Systems With Capacity Constraints

In this paper we propose a load balancing problem formulation where agents cooperate with the aim of simultaneously minimizing both the workload disparity among the agents and the overall workload transfer, under network capacity constraints. Notably, in our computational setting, the network is not just a device for the distributed solution of an optimization problem; on the contrary, the problem shares the same sparsity pattern as the network, and this aspect allows to solve it without the need for the agents to store large amount of data. In particular, while the load balancing process occurs over directed links, agents' communication is assumed to be bidirectional. For this optimization setting, first, an optimality condition is derived; then, a provably convergent distributed algorithm to compute the optimal solution is developed, and an upper bound on the convergence rate is characterized. Simulation results are provided to corroborate the validity and performance of our theoretical findings.

Software defined network‐based multipath state‐aware routing with traffic prediction in satellite network

AbstractUneven traffic demand in satellite networks can lead to link congestion and influence network communication quality. To tackle this problem, we propose a state‐aware routing algorithm based on traffic prediction to disperse network traffic. Reducing the onboard processing requirements, the routing algorithm in this paper introduces a software‐defined network to decouple the control plane and data plane of the satellite network. Also, to better sense the trend of network state, the routing algorithm devises a Spatial‐Temporal Attention Fusion Graph Neural Network (STAFGNN) to predict the future network state by capturing the spatial‐temporal correlation of satellite network traffic. In the control plane, the routing algorithm senses the network state by predicting the future satellite traffic and aggregates the real‐time states of neighboring satellites to identify the load level of the zone. The data plane forwards data based on the control information. Based on the routing algorithm in this paper, multipath routing is designed to reduce the probability of link congestion by dispersing each end‐to‐end traffic. The simulation results demonstrate that the routing algorithm in this paper reduces the number of congestion links and balances the load distribution. The proposed algorithm provides an idea to introduce deep learning to solve the load balancing problem in satellite networks.

LBCC-Hung: A load balancing protocol for cloud computing based on Hungarian method

Cloud Computing can be defined as enabling computing resources to whoever want remotely upon demand. This necessarily requires using virtualization. A virtual machine (VM) is an emulation of a computer that runs in virtualization software. Tasks coming from different users are passed to the virtual machines to be processed. This paper studies the load balancing problem among various VMs; to ensure that the network resources are distributed in a fair way between various clients. This paper proposes solving the load balancing problem using a combinatorial optimization approach named the Hungarian method. The proposed protocol is named LBCC-Hung (Load Balancing Protocol for Cloud Computing Based on Hungarian Method). Using simulation, the performance of LBCC-Hung is measured and compared with two well-known methods; MIN-MIN and First Come First Serve FCFS methods. The simulation results proved that LBCC-Hung overperforms the others two protocols, in terms of both the Makespan and the throughput and the virtual machine utilization deviation.

TFUZZY-OF: a new method for routing protocol for low-power and lossy networks load balancing using multi-criteria decision-making

The internet of things (IoT) based on a network layer perspective includes low-power and lossy networks (LLN) that are limited in terms of power consumption, memory, and energy usage. The routing protocol used in these networks is called routing over low-power and lossy networks (RPL). Therefore, the IoT networks include smart objects that need multiple routing for their interconnections which makes traffic load balancing techniques indispensable to RPL routing protocol. In this paper, we propose a method based on fuzzy logic and the technique for the order of prioritization by similarity to the ideal solution (TOPSIS) as a well-known multi-criteria decision-making method to solve the load balancing problem by routing metrics composition. For this purpose, a combination of both link and node routing metrics namely hop count, expected transmission count, and received signal strength indicator is used. The results of simulations show that this method can increase the quality of services in terms of packet delivery ratio and average end-to-end delay.

Reinforcement learning for communication load balancing: approaches and challenges

The amount of cellular communication network traffic has increased dramatically in recent years, and this increase has led to a demand for enhanced network performance. Communication load balancing aims to balance the load across available network resources and thus improve the quality of service for network users. Most existing load balancing algorithms are manually designed and tuned rule-based methods where near-optimality is almost impossible to achieve. Furthermore, rule-based methods are difficult to adapt to quickly changing traffic patterns in real-world environments. Reinforcement learning (RL) algorithms, especially deep reinforcement learning algorithms, have achieved impressive successes in many application domains and offer the potential of good adaptabiity to dynamic changes in network load patterns. This survey presents a systematic overview of RL-based communication load-balancing methods and discusses related challenges and opportunities. We first provide an introduction to the load balancing problem and to RL from fundamental concepts to advanced models. Then, we review RL approaches that address emerging communication load balancing issues important to next generation networks, including 5G and beyond. Finally, we highlight important challenges, open issues, and future research directions for applying RL for communication load balancing.

EPTAS for load balancing problem on parallel machines with a non-renewable resource

The problem considered is the non-preemptive scheduling of independent jobs that consume a resource (which is non-renewable and replenished regularly) on parallel uniformly related machines. The input defines the speed of machines, size of jobs, the quantity of the resource required by the jobs, the replenished quantities, and replenishment dates of the resource. Every job can start processing only after the required quantity of the resource is allocated to the job. The objective function is a generalization of makespan minimization and minimization of the lp-norm of the vector of loads of the machines. We present an EPTAS for this problem. Prior to our work only a PTAS was known in this non-renewable resource settings only for the special case of our problem of makespan minimization on identical machines.

Efficient Load Balancing in WSN Using Quasi – oppositional Based Jaya Optimization with Cluster Head Selection

Researchers have been paying close attention to the wireless sensor (WSN) networks area because of its variety of applications, including industrial management, human detection, and health care management. In Wireless Sensor (WSN) Network, consumption of efficient energy is a challenging problem. Many clustering techniques were used for balancing the load of WSN network. In clustering, the cluster head (CH) is selected as a relay node with greater power which is compared with the nodes of non-CH. In the existing system, it uses LBC-COFL algorithm to reduce the energy consumption problem. To overcome this problem, the proposed system uses Quasi oppositional based Jaya load balancing strategy with cluster head (QOJ-LCH) selection protocol to boost the lifespan of network and energy consumption. The QOJ-LCH method improves the relay nodes life and shares the load on relay nodes equitably across the network to enhance the lifespan. It also reduces the load-balancing problems in Wireless Sensor networks. It uses two routing methods single-hop and multiple-hop. The proposed QOJ-LCH with cluster head selection method enhances the network’s lifespan, total amount of power utilization and the active sensor devices present in the Single-hop routing,it worked with 1600 rounds in network and 300 sensor nodes, for Multiple-hop routing, it worked with 1800 rounds in network and 350 sensor nodes. It achieves better performance, scalability and reliability.