Load Balancing Problem Research Articles

Cognitive Load Balancing Approach for 6G MEC Serving IoT Mashups

The sixth generation (6G) of communication networks represents more of a revolution than an evolution of the previous generations, providing new directions and innovative approaches to face the network challenges of the future. A crucial aspect is to make the best use of available resources for the support of an entirely new generation of services. From this viewpoint, the Web of Things (WoT), which enables Things to become Web Things to chain, use and re-use in IoT mashups, allows interoperability among IoT platforms. At the same time, Multi-access Edge Computing (MEC) brings computing and data storage to the edge of the network, which creates the so-called distributed and collective edge intelligence. Such intelligence is created in order to deal with the huge amount of data to be collected, analyzed and processed, from real word contexts, such as smart cities, which are evolving into dynamic and networked systems of people and things. To better exploit this architecture, it is crucial to break monolithic applications into modular microservices, which can be executed independently. Here, we propose an approach based on complex network theory and two weighted and interdependent multiplex networks to address the Microservices-compliant Load Balancing (McLB) problem in MEC infrastructure. Our findings show that the multiplex network representation represents an extra dimension of analysis, allowing to capture the complexity in WoT mashup organization and its impact on the organizational aspect of MEC servers. The impact of this extracted knowledge on the cognitive organization of MEC is quantified, through the use of heuristics that are engineered to guarantee load balancing and, consequently, QoS.

Hybrid Nearest-Neighbor Ant Colony Optimization Algorithm for Enhancing Load Balancing Task Management

Many computer problems that arise from real-world circumstances are NP-hard, while, in the worst case, these problems are generally assumed to be intractable. Existing distributed computing systems are commonly used for a range of large-scale complex problems, adding advantages to many areas of research. Dynamic load balancing is feasible in distributed computing systems since it is a significant key to maintaining stability of heterogeneous distributed computing systems (HDCS). The challenge of load balancing is an objective function of optimization with exponential complexity of solutions. The problem of dynamic load balancing raises with the scale of the HDCS and it is hard to tackle effectively. The solution to this unsolvable issue is being explored under a particular algorithm paradigm. A new codification strategy, namely hybrid nearest-neighbor ant colony optimization (ACO-NN), which, based on the metaheuristic ant colony optimization (ACO) and an approximate nearest-neighbor (NN) approaches, has been developed to establish a dynamic load balancing algorithm for distributed systems. Several experiments have been conducted to explore the efficiency of this stochastic iterative load balancing algorithm; it is tested with task and nodes accessibility and proved to be effective with diverse performance metrics.

Agile Support Vector Machine for Energy-efficient Resource Allocation in IoT-oriented Cloud using PSO

Over the years cloud computing has seen significant evolution in terms of improvement in infrastructure and resource provisioning. However the continuous emergence of new applications such as the Internet of Things (IoTs) with thousands of users put a significant load on cloud infrastructure. Load balancing of resource allocation in cloud-oriented IoT is a critical factor that has a significant impact on the smooth operation of cloud services and customer satisfaction. Several load balancing strategies for cloud environment have been proposed in the past. However the existing approaches mostly consider only a few parameters and ignore many critical factors having a pivotal role in load balancing leading to less optimized resource allocation. Load balancing is a challenging problem and therefore the research community has recently focused towards employing machine learning-based metaheuristic approaches for load balancing in the cloud. In this paper we propose a metaheuristics-based scheme Data Format Classification using Support Vector Machine (DFC-SVM), to deal with the load balancing problem. The proposed scheme aims to reduce the online load balancing complexity by offline-based pre-classification of raw-data from diverse sources (such as IoT) into different formats e.g. text images media etc. SVM is utilized to classify “n” types of data formats featuring audio video text digital images and maps etc. A one-to-many classification approach has been developed so that data formats from the cloud are initially classified into their respective classes and assigned to virtual machines through the proposed modified version of Particle Swarm Optimization (PSO) which schedules the data of a particular class efficiently. The experimental results compared with the baselines have shown a significant improvement in the performance of the proposed approach. Overall an average of 94% classification accuracy is achieved along with 11.82% less energy 16% less response time and 16.08% fewer SLA violations are observed.

Virtual Machine Allocation Policy for Load Balancing

This paper focuses on the VM allocation policies for load balancing in cloud computing environment. Intermittent nature of balancing the load scheme into the cloud computing becomes a challenging job and it also affects the load balancing of the cloud. The suggested proposed model generates and step-up the VM allocation policies but also transforms the generated cloud workload. Furthermore, to improve the workload distribution of workload and stability of the overall cloud computing environment the load balancing algorithm is most important for load balancing. The work of load balancing is equally effective in the cloud computing environment and it is most essential one for load balancing algorithms to take care of all issues at the time of the work load. The researchers studied different algorithms to solve the problems of load balancing that generate problems during the distribution of workloads. The analysis VM allocation policies are tested on CloudSim environment and the results, and discussion is about to which one VM allocation policy is superior.

A novel top‐k key node query problem in subgraph matching and its greedy strategy

AbstractTop‐k node selection in graph data is an essential problem in computer science and applications. In view of an important issue in the field of graph data, subgraph matching issue, we define the problem and propose its method for the top‐k key node query w.r.t. the subgraph matching. Unlike the general top‐k query problem, we aim to find out k nodes that make the matching subgraphs in data graph G that are covered by the k nodes as more as possible. This is a problem of the maximum coverage of subgraph matching, which belongs to the NP‐hard problem. We study the problem based on a greedy algorithm and give an intuitive solution. Considering the characteristics of the top‐k problem, we propose an improved and more efficient greedy algorithm. Experiments on real social network graph data set (Twitter) show that the related results represent the key nodes that can better reveal the essential characteristics of the query graph in the data graph G. The key node query problem in subgraph matching proposed in this article may have extensive applications in reality, such as the assessment of the influence of specific group members in social network, the detection of abnormal communication in a computer communication network, the road traffic evaluation and load balance problem in a road traffic network, and so on.

Domain decomposition in the GPU-accelerated Shift Monte Carlo code

The GPU solver within the Shift continuous-energy Monte Carlo neutron transport code has been extended to provide domain decomposition in addition to domain replication to enable the solution of problems with memory requirements exceeding the capacity of a single GPU. The strategy follows the Multiple Set, Overlapping Domain (MSOD) approach that is used in Shift’s CPU solver and integrates into the event-based algorithm used for Shift’s GPU solver. Furthermore, the ability to assign processors to spatial domains non-uniformly has been maintained. Two different approaches for communicating particle data between domains are considered, and multiple criteria for load balancing problems have been investigated. Numerical results are presented for both fresh and depleted small modular nuclear reactor (SMR) cores. A parallel efficiency of approximately 80% was achieved with up to 16 spatial domains measured relative to full domain replication. A scaling study on the Summit supercomputer demonstrates a weak scaling parallel efficiency of over 90% on over 24000 GPUs.

Self-Learning Threshold-Based Load Balancing

We consider a large-scale service system where incoming tasks have to be instantaneously dispatched to one out of many parallel server pools. The user-perceived performance degrades with the number of concurrent tasks and the dispatcher aims at maximizing the overall quality of service by balancing the load through a simple threshold policy. We demonstrate that such a policy is optimal on the fluid and diffusion scales, while only involving a small communication overhead, which is crucial for large-scale deployments. In order to set the threshold optimally, it is important, however, to learn the load of the system, which may be unknown. For that purpose, we design a control rule for tuning the threshold in an online manner. We derive conditions that guarantee that this adaptive threshold settles at the optimal value, along with estimates for the time until this happens. In addition, we provide numerical experiments that support the theoretical results and further indicate that our policy copes effectively with time-varying demand patterns. Summary of Contribution: Data centers and cloud computing platforms are the digital factories of the world, and managing resources and workloads in these systems involves operations research challenges of an unprecedented scale. Due to the massive size, complex dynamics, and wide range of time scales, the design and implementation of optimal resource-allocation strategies is prohibitively demanding from a computation and communication perspective. These resource-allocation strategies are essential for certain interactive applications, for which the available computing resources need to be distributed optimally among users in order to provide the best overall experienced performance. This is the subject of the present article, which considers the problem of distributing tasks among the various server pools of a large-scale service system, with the objective of optimizing the overall quality of service provided to users. A solution to this load-balancing problem cannot rely on maintaining complete state information at the gateway of the system, since this is computationally unfeasible, due to the magnitude and complexity of modern data centers and cloud computing platforms. Therefore, we examine a computationally light load-balancing algorithm that is yet asymptotically optimal in a regime where the size of the system approaches infinity. The analysis is based on a Markovian stochastic model, which is studied through fluid and diffusion limits in the aforementioned large-scale regime. The article analyzes the load-balancing algorithm theoretically and provides numerical experiments that support and extend the theoretical results.

Multi Objective PSO with Passive Congregation for Load Balancing Problem

High-level architecture (HLA) and Distributed Interactive Simulation (DIS) are commonly used for the distributed system. However, HLA suffers from a resource allocation problem and to solve this issue, optimization of load balancing is required. Efficient load balancing can minimize the simulation time of HLA and this optimization can be done using the multi-objective evolutionary algorithms (MOEA). Multi-Objective Particle Swarm Optimization (MOPSO) based on crowding distance (CD) is a popular MOEA method used to balance HLA load. In this research, the efficiency of MOPSO-CD is further improved by introducing the passive congregation (PC) method. Several simulation tests are done on this improved MOPSO-CD-PC method and the results showed that in terms of Coverage, Spacing, Non-dominated solutions and Inverted generational distance metrics, the MOPSO-CD-PC performed better than the previous MOPSO-CD algorithm. Hence, it can be a useful tool to optimize the load balancing problem in HLA.

Adjusted and Robust Routing Update Algorithms for Internet of Things

In this paper, two enhanced Trickle-based route update and maintenance algorithms for Low-Power and Lossy Networks (LLNs), called Adaptive and Robust Trickle and Adjusted-Trickle algorithms (AR-Trickle and Trickle-A) are proposed. The purpose is to tackle the main limitations of the standardized route update Trickle algorithm in this type of networks, in addition to the load-balancing problem of the IPv6 Routing Protocol for LLNs (RPL). In the proposed algorithms, new approaches for dynamically choosing the values of the redundancy coefficient (k) and the minimum interval size (Imin) are introduced. In addition, new mechanisms for skipping intervals to double the current interval size (I) are introduced. Moreover, new probabilistic approaches for transmitting and suppressing scheduled transmissions are introduced. In addition, new techniques for selecting the listen-only period and transmission window are introduced. Moreover, in order to evaluate the proposed algorithms, extensive simulation experiments have been conducted under different conditions and scenarios. The experiments results have showed that Trickle-A outperforms the standard Trickle and achieves better efficiency, with high stability, reliability, and scalability for different applications. Thanks to the stepwise approach, this algorithm follows in dealing with network variations by gradually increasing and decreasing parameters and variables values. On the other hand, AR-Trickle outperforms both Trickle-A and the standard Trickle and has achieved strong performance, by effectively reducing control-plane overhead, convergence time, and power consumption by up to 68%, 47%, and 18% respectively, while maintaining nearly the same level of reliability in term of Packet Delivery Ratio (PDR).

Integrated Optimization Method of IPPS under TOU and Tiered Electricity Price

Energy-saving production is one of the issues that must be paid attention to by today’s manufacturing enterprises. Aiming at the problem of integrated process planning and scheduling (IPPS) in the manufacturing process, considering Time-of-Use (TOU) and tiered electricity price, this paper systematically studies the energy-saving scheduling problem in order to reduce the power consumption in processing and production. To establish the multiobjective optimization mathematical model of the problem, the load balancing problem of the equipment is considered, the minimization of the power consumption and the maximum load of the equipment are taken as the optimization objectives. Then, considering the constraints of resource and multiprocess, the switching strategy of the equipment in idle time is introduced, including shutdown and restart operations. In order to solve the model easily, a multiobjective firefly algorithm (MOFA) based on five-layer coding is designed, and the elite strategy is introduced to protect the excellent firefly individuals in the iterative population. Finally, through a specific example, the Pareto solution set is obtained, which provides a reference scheme for decision-makers, and verifies the correctness of the model and the effectiveness of the algorithm.

Accelerated Cuckoo Search With Extended Diversification and Intensification

Metaheuristics have been great to solve NP-hard class problems in the deterministic time, but due to so many parameter settings, they lack in generality (i.e., not easy to implement on all types of problems) and also lack in global search. But the cuckoo search (CS) algorithm has only one parameter as input and also has a good reachable probability to global solution due to Levy flight. But this algorithm lacks self-adaptive parameters and extended strategies. In this paper, a deep study and improvement of cuckoo search performance has been done by introducing self-adaptive step size, extended alien egg discovery replacement (on each dimension with the use of good neighbor study), and adaptive discovery probability, and it has been named accelerated cuckoo search (ACS). Then this ACS has been utilized as an example in the load balancing problem in cloud with minimum makespan time as an objective parameter to evaluate the performance of ACS over CS. Furthermore, to validate ACS superiority over CS in all problems, these have been successfully compared on a few benchmark functions.

A Multi-Objective Genetic Algorithm-Based Resource Scheduling in Mobile Cloud Computing

Mobile cloud computing is an emerging technology in recent years. This technology reduces battery consumption and execution time by executing mobile applications in remote cloud server. The virtual machine (VM) load balancing among cloudlets in MCC improves the performance of application in terms of response time. Genetic algorithm (GA) is popular for providing optimal solution for load balancing problems. GA can perform well in both homogeneous and heterogeneous environments. In this paper, the authors consider multi-objective genetic algorithm for load balancing in MCC (MOGALMCC) environment. In MOGALMCC, they consider distance, bandwidth, memory, and cloudlet server load to find optimal cloudlet before scheduling VM in another cloudlet. The framework MOGALMCC aims to improve response time as well as minimizes VM failure rate. The experiment result shows that proposed model performed well by reducing execution time and task waiting time at server.

Load balancing method for heterogeneous CFD algorithms

Abstract. The problem of load balancing for unstructured heterogeneous numerical algorithms for simulation of physical processes is considered. A computational distribution method for hybrid supercomputers with multicore CPUs and massively parallel accelerators is described. The load balancing procedure includes determination of dual graph vertices and edges weights, devices’ performance test and two-level decomposition of the computational mesh based on domain decomposition method. First level decomposition involves the graph partitioning between supercomputer nodes. On the second level node subdomains are partitioned between the MPI- processes running on the nodes. The details of the proposed approach are considered on the example of an unstructured finite-volume algorithm for modeling the Navier-Stokes equations with polynomial reconstruction of variables and explicit time integration scheme. The parallel version of the algorithm is developed using the MPI, OpenMP and CUDA programming models. The parameters of performance, parallel efficiency and scalability of the heterogeneous program are given. The results mentioned are obtained during the simulation of a supersonic flow around a sphere on a mixed mesh consisting of tetrahedrons, triangular prisms, quadrangular pyramids and hexagons.

Affinity-Based Task Scheduling on Heterogeneous Multicore Systems Using CBS and QBICTM

This work presents the grouping of dependent tasks into a cluster using the Bayesian analysis model to solve the affinity scheduling problem in heterogeneous multicore systems. The non-affinity scheduling of tasks has a negative impact as the overall execution time for the tasks increases. Furthermore, non-affinity-based scheduling also limits the potential for data reuse in the caches so it becomes necessary to bring the same data into the caches multiple times. In heterogeneous multicore systems, it is essential to address the load balancing problem as all cores are operating at varying frequencies. We propose two techniques to solve the load balancing issue, one being designated “chunk-based scheduler” (CBS) which is applied to the heterogeneous systems while the other system is “quantum-based intra-core task migration” (QBICTM) where each task is given a fair and equal chance to run on the fastest core. Results show 30–55% improvement in the average execution time of the tasks by applying our CBS or QBICTM scheduler compare to other traditional schedulers when compared using the same operating system.

LBPSGORA: Create Load Balancing with Particle Swarm Genetic Optimization Algorithm to Improve Resource Allocation and Energy Consumption in Clouds Networks

Due to the purpose of this study that reducing power consumption in the cloud network is based on load balancing, the fitness function measures the load balance between cloud network and servers (the hosts). This technique is appropriate for handling the resource optimization challenges, due to the ability to convert the load balancing problem into an optimization problem (reducing imbalance cost). In this research, combining the results of the particle swarm genetic optimization (PSGO) algorithm and using a combination of advantages of these two algorithms lead to the improvement of the results and introducing a suitable solution for load balancing operation, because in the proposed approach (LBPSGORA), instead of randomly assigning the initial population in the genetic algorithm, the best result is procured by putting the initial population. The LBPSGORA method is compared with PSO, GA, and hybrid GA-PSO. The execution cost, load balancing, and makespan have been evaluated and our method has performed better than similar methods.

Hybrid load balance based on genetic algorithm in cloud environment

Load balancing is an efficient mechanism to distribute loads over cloud resources in a way that maximizes resource utilization and minimizes response time. Metaheuristic techniques are powerful techniques for solving the load balancing problems. However, these techniques suffer from efficiency degradation in large scale problems. This paper proposes three main contributions to solve this load balancing problem. First, it proposes a heterogeneous initialized load balancing (HILB) algorithm to perform a good task scheduling process that improves the makespan in the case of homogeneous or heterogeneous resources and provides a direction to reach optimal load deviation. Second, it proposes a hybrid load balance based on genetic algorithm (HLBGA) as a combination of HILB and genetic algorithm (GA). Third, a newly formulated fitness function that minimizes the load deviation is used for GA. The simulation of the proposed algorithm is implemented in the cases of homogeneous and heterogeneous resources in cloud resources. The simulation results show that the proposed hybrid algorithm outperforms other competitor algorithms in terms of makespan, resource utilization, and load deviation.

Revenue optimization in energy networks involving self-scheduled demand and a smart grid

In this paper, we address a day-ahead pricing and load balancing problem, within an environment involving self-scheduled users whose utilities are optimized via a smart grid. The model is formulated as a mixed integer bilevel program for which we propose a single level reformulation. Next, we design two heuristic algorithms which, by relying on the structure of the problem, provide high quality solutions in moderate computation time.

A new SLA-aware method for discovering the cloud services using an improved nature-inspired optimization algorithm.

Cloud computing is one of the most important computing patterns that use a pay-as-you-go manner to process data and execute applications. Therefore, numerous enterprises are migrating their applications to cloud environments. Not only do intensive applications deal with enormous quantities of data, but they also demonstrate compute-intensive properties very frequently. The dynamicity, coupled with the ambiguity between marketed resources and resource requirement queries from users, remains important issues that hamper efficient discovery in a cloud environment. Cloud service discovery becomes a complex problem because of the increase in network size and complexity. Complexity and network size keep increasing dynamically, making it a complex NP-hard problem that requires effective service discovery approaches. One of the most famous cloud service discovery methods is the Ant Colony Optimization (ACO) algorithm; however, it suffers from a load balancing problem among the discovered nodes. If the workload balance is inefficient, it limits the use of resources. This paper solved this problem by applying an Inverted Ant Colony Optimization (IACO) algorithm for load-aware service discovery in cloud computing. The IACO considers the pheromones’ repulsion instead of attraction. We design a model for service discovery in the cloud environment to overcome the traditional shortcomings. Numerical results demonstrate that the proposed mechanism can obtain an efficient service discovery method. The algorithm is simulated using a CloudSim simulator, and the result shows better performance. Reducing energy consumption, mitigate response time, and better Service Level Agreement (SLA) violation in the cloud environments are the advantages of the proposed method.

DQN as an alternative to Market-based approaches for Multi-Robot processing Task Allocation (MRpTA)

Multi-robot task allocation (MRTA) problems require that robots make complex choices based on their understanding of a dynamic and uncertain environment. As a distributed computing system, the Multi-Robot System (MRS) must handle and distribute processing tasks (MRpTA). Each robot must contribute to the overall efficiency of the system based solely on a limited knowledge of its environment. Market-based methods are a natural candidate to deal processing tasks over a MRS but recent and numerous developments in reinforcement learning and especially Deep Q-Networks (DQN) provide new opportunities to solve the problem. In this paper we propose a new DQN-based method so that robots can learn directly from experience, and compare it with Market-based approaches as well with centralized and purely local solutions. Our study shows the relevancy of learning-based methods and also highlight research challenges to solve the processing load-balancing problem in MRS.

Efficiency and scalability of multi-lane capsule networks (MLCN)

Some Deep Neural Networks (DNN) have what we call lanes, or they can be reorganized as such. Lanes are paths in the network which are data-independent and typically learn different features or add resilience to the network. Given their data-independence, lanes are amenable for parallel processing. The Multi-lane CapsNet (MLCN) is a proposed reorganization of the Capsule Network which is shown to achieve better accuracy while bringing highly-parallel lanes. However, the efficiency and scalability of MLCN had not been systematically examined. In this work, we study the MLCN network with multiple GPUs finding that it is 2x more efficient than the original CapsNet when using model-parallelism. We introduce the load balancing problem of distributing heterogeneous lanes in homogeneous or heterogeneous accelerators and show that a simple greedy heuristic can be almost 50% faster than a naïve random approach. Further, we show that we can generate MLCN models with heterogeneous lanes with a balanced fit for a given set of devices. We describe a Neural Architectural Search generating MLCN models matching the device's memory that are load balanced. This search discovered models with 18.6% better accuracy for CIFAR-10.