Degree Of Imbalance Research Articles

A chameleon and remora search optimization algorithm for handling task scheduling uncertainty problem in cloud computing

Task scheduling in cloud computing is responsible for serving the user requirements. The scheduling strategy must handle the problems of high load over virtual machines (VMs), high-cost consumption and lengthier scheduling time effectively. The greatest challenge in the cloud computing environment is achieving the intended outcome of task scheduling under the uncertain user request demands as it is responsible for assigning specific resources to requests for achieving effective task completion. However, most of the task scheduling approaches contributed to the literature mainly focused on the design and development of scheduling algorithms but ignored to explore the impact of uncertain factors such as millions of instructions per second (MIPS) and network bandwidth during the scheduling process. In this paper, A Chameleon and Remora Search Optimization Algorithm (CRSOA) is proposed for achieving efficient scheduling process by exploring the impact of MIPS and network bandwidth which directly affects the virtual machine (VM) performance. Further the work includes the uncertainty factors of task completion rate, load balance, scheduling cost and makespan in a simultaneous manner during the process of scheduling. It is formulated a multi-objective cloud task scheduling optimization model by integrating the merits of Chameleon Search Algorithm (CSA) and Remora Search Optimization Algorithm (RSOA) using a greedy methodology for simulating the real cloud computing task scheduling process. The simulation results evidently confirmed that the proposed CRSOA approach is minimizing the completion time and effective in handling the load balancing between the available VMs against other competitive metaheuristic task scheduling algorithms. The experimental investigation of this CRSOA confirmed its predominance in minimizing the makespan by 18.96%, cost by 22.18%, and degree of imbalance by 20.54%, compared to the baseline approaches with different number of tasks and VMs.

Prevalence of chromosomal alterations in first-trimester spontaneous pregnancy loss

Pregnancy loss is often caused by chromosomal abnormalities of the conceptus. The prevalence of these abnormalities and the allocation of (ab)normal cells in embryonic and placental lineages during intrauterine development remain elusive. In this study, we analyzed 1,745 spontaneous pregnancy losses and found that roughly half (50.4%) of the products of conception (POCs) were karyotypically abnormal, with maternal and paternal age independently contributing to the increased genomic aberration rate. We applied genome haplarithmisis to a subset of 94 pregnancy losses with normal parental and POC karyotypes. Genotyping of parental DNA as well as POC extra-embryonic mesoderm and chorionic villi DNA, representing embryonic and trophoblastic tissues, enabled characterization of the genomic landscape of both lineages. Of these pregnancy losses, 35.1% had chromosomal aberrations not previously detected by karyotyping, increasing the rate of aberrations of pregnancy losses to 67.8% by extrapolation. In contrast to viable pregnancies where mosaic chromosomal abnormalities are often restricted to chorionic villi, such as confined placental mosaicism, we found a higher degree of mosaic chromosomal imbalances in extra-embryonic mesoderm rather than chorionic villi. Our results stress the importance of scrutinizing the full allelic architecture of genomic abnormalities in pregnancy loss to improve clinical management and basic research of this devastating condition.

Reusability report: Learning the transcriptional grammar in single-cell RNA-sequencing data using transformers

The rise of single-cell genomics is an attractive opportunity for data-hungry machine learning algorithms. The scBERT method, inspired by the success of BERT (‘bidirectional encoder representations from transformers’) in natural language processing, was recently introduced by Yang et al. as a data-driven tool to annotate cell types in single-cell genomics data. Analogous to contextual embedding in BERT, scBERT leverages pretraining and self-attention mechanisms to learn the ‘transcriptional grammar’ of cells. Here we investigate the reusability beyond the original datasets, assessing the generalizability of natural language techniques in single-cell genomics. The degree of imbalance in the cell-type distribution substantially influences the performance of scBERT. Anticipating an increased utilization of transformers, we highlight the necessity to consider data distribution carefully and introduce a subsampling technique to mitigate the influence of an imbalanced distribution. Our analysis serves as a stepping stone towards understanding and optimizing the use of transformers in single-cell genomics.

Optimizing Workload Scheduling in Cloud Paradigm using Robust Neutrosophic C-Means Clustering Boosted with Fish School Search

In the present internet world, accessing cloud resources for a low cost, according to their needs, is available to all users. Sharing resources is becoming increasingly necessary as people complete their activities in the cloud. It becomes essential for distributed workloads to be optimized to perform efficient workload scheduling and progressing resource utilization in a cloud environment. Scheduling cloud resources considerably benefits from the invention of machine learning and metaheuristic models to address this scenario. Though many existing algorithms are developed in cloud-based task scheduling using unsupervised clustering methods, the problem of unknown task requirements or resource availability in adverse conditions is still challenging. In this study, an uncertainty-based unsupervised technique is constructed to group incoming tasks according to the required resources, and it is scheduled to the most suitable resources more prominently. This paper introduced a Robust Neutrosophic C-Means Clustering boosted with the fish school search algorithm (RNCM-FSSA) for clustering the incoming tasks and the resources based on their requirement and availability. With the degree of indeterminacy, neutrosophic C-means discriminating the deterministic and indeterministic schemes and scheduling them to the optimal resources more effectively. Using the fitness value computed by FFSA, the potential cluster centroids are utilized for clustering, thus avoiding the early convergence in the grouping process. The simulation results explore that the robustness of the proposed RCNM-SSA achieves better resource utilization, the degree of imbalance is minimal, and computation complexity is also considerably decreased compared with other unsupervised models.

The comprehensive analysis of thalassemia alleles (CATSA) based on single-molecule real-time technology (SMRT) is a more powerful strategy in the diagnosis of thalassemia caused by rare variants

Thalassemia is one of the most widely distributed monogenic disorders in the world and affects the largest number of people. It can manifest a wide spectrum of phenotypes from asymptomatic to fatal, which is associated with the degree of imbalance between α- and β-globin chains. Therefore, individuals with different genotypes could present with a similar phenotype. Genetic analysis is always needed to make a correct diagnosis. However, routine genetic analysis of thalassemia used in the Chinese population identifies only 23 common variants, resulting in many cases undiagnosed or being misdiagnosed. In this study, we applied a long-read sequencing-based approach termed comprehensive analysis of thalassemia alleles (CATSA) to 30 subjects whose hematologic screening results could not be explained by the routine genetic test results. The identification of additional variants and the correction of genotypes allowed the interpretation of the clinical phenotype in 24 subjects, which have been confirmed to be correct by independent experiments. Moreover, we identified a novel 8.4-kb deletion containing the entire HBB and HBD genes as well as part of the HBBP1 gene, expanding the genotype spectrum of β-thalassemia. CATSA showed a great advantage over other genetic tests in the diagnosis of thalassemia caused by rare variants.

A Novel Hybrid MSA-CSA Algorithm for Cloud Computing Task Scheduling Problems

Recently, the dynamic distribution of resources and task scheduling has played a critical role in cloud computing to achieve maximum storage and performance. The allocation of computational tasks in the cloud is a complicated process that can be affected by some factors, such as available network bandwidth, makespan, and cost considerations. However, these allocations are always non-symmetric. Therefore, it is crucial to optimize available bandwidth for efficient cloud computing task scheduling. In this research, a novel swarm-based task scheduling with a security approach is proposed to optimize the distribution of tasks using available resources and encode cloud information during task scheduling. It can combine the Moth Swarm Algorithm (MSA) with the Chameleon Swarm Algorithm (CSA) for the task scheduling process and utilizes the Polymorphic Advanced Encryption Standard (P-AES) for information security of cloud scheduled tasks. The approach offers a new perspective for utilizing swarm intelligence algorithms to optimize cloud task scheduling. The integration of MSA and CSA with P-AES enables the approach to provide efficient and secure task scheduling by exploiting the strengths of used algorithms. The study evaluates the performance of the proposed approach in terms of the degree of imbalance, makespan, resource utilization, cost, average waiting time, response time, throughput, latency, execution time, speed, and bandwidth utilization. The simulation is carried out using a wide range of tasks from 1000 to 5000. The results show that the approach provides an innovative solution to the challenges of task scheduling in cloud environments and improves the performance of cloud services in terms of effectiveness and security measures.

Collaborative Development and Transportation Volume Regulation Strategy for an Urban Agglomeration

Transportation plays an important role in urban development and the formation of urban agglomerations. Indexes including urban centrality, urban development intensity, and degree of urban development imbalance are defined to measure the level of urban development, and are taken as the basis for transportation regulation within urban agglomerations. Regulation of transportation volume is divided into static and dynamic regulation, and this paper studies static regulation. There are two purposes for static regulation. One is to solve the problems of unbalanced urban development and collaborative development, and the other is to solve the problem of rational utilization of the highway transport network in an urban agglomeration so that the total transportation volume of the urban agglomeration does not exceed the total transportation volume that the transport network can bear, realizing coordinated transport, improving transport efficiency, and reducing traffic congestion and traffic accidents. A distributed intelligent regulation model based on the principle of game control is proposed, which is divided into three layers: macro-regulation (government layer), meso-regulation (urban agglomeration layer), and micro-regulation (individual city game layer). The regulation strategies and methods of the urban agglomeration layer and individual city game layer are given, and are verified and illustrated using as the research object called the Jilin Province urban agglomeration in the northeast of China. The paper contributes to the field by presenting innovative research and provides important theories and methods for collaborative development and transportation within urban agglomerations.

Self-Adaptive Imbalanced Domain Adaptation With Deep Sparse Autoencoder

Domain adaptation aims to transfer knowledge between different domains to develop an effective hypothesis in the target domain with scarce labeled data, which is an effective method for remedying the problem of labeled data requirement in deep learning. In reality, it is unavoidable that the dataset has a large gap in the number of positive and negative instances across different categories in source and target domains, which is the imbalanced domain adaptation problem. However, since the imbalanced degree always varies greatly in different source and target domains datasets, most existing imbalanced domain adaptation models fix the imbalanced parameters which can not adapt to the change of the proportion between positive and negative instances in different domains. To address this problem, in this paper, we propose a self-adaptive imbalanced domain adaptation method via deep sparse autoencoder, which can adjust the model automatically according to the imbalanced extent for bridging the chasm of domains. More specifically, the self-adaptive imbalanced cross entropy loss is designed for emphasizing more on minority categories and compensating the bias of training loss automatically. In addition, to alleviate the deficient problem of labeled data, we further propose the unlabeled information incorporating method by minimizing the distribution discrepancy of high-level representation space between the source and target domains. Experiments on several real-world datasets demonstrate the effectiveness of our method compared to other state-of-the-art methods.

A multi-objective complex product assembly scheduling problem considering transport time and worker competencies

The hybrid flow shop scheduling problem (HFSP) is a research hotspot in the shop scheduling problem. However, few studies have investigated HFSP involving parallel machine scheduling and worker competencies. Therefore, this study investigates a complex product assembly line scheduling problem considering parallel team scheduling, worker competencies, and transport time. The makespan, transport time, imbalance degree of team workload, and imbalance degree of cycle time are taken as optimization objectives. First, a mathematical model considering transport time and worker competencies is developed, and then a mixed encoding and decoding method is proposed. Second, an algorithm that hybridizes the genetic algorithm and simulated annealing algorithm is proposed, involving an improved Nawaz-Enscore-Ham heuristic method and a strengthened elite retention strategy to improve the quality of the solution. Finally, based on nine examples generated from real production statuses, the proposed algorithm is compared with the other four algorithms. The results show that the proposed algorithm is superior in terms of the quality and efficiency of solutions.

Semi-supervised variational bi-directional sampling on multi-class imbalanced electric power data for fault diagnosis

Imbalanced data is one of the inevitable problems in electric power industrial fault diagnosis, which will affect the performance of classification models. Therefore, a semi-supervised variational bi-directional sampling (SVBDS) method is proposed to balance the dataset with data-level and feature-level combined. First, a novel bi-directional sampling framework suitable for the dataset with various imbalance degrees between multi classes is built, which corresponds with the real dataset structure. This framework can separate normal data and balance the rest fault sets. Second, a two-step synthesis sampling method is proposed for minority fault categories based on generative model to obtain homo-distributed and diverse data. This method can quantitatively generate specific categories and ensure generative quality. The experimental results on the actual industrial power transformer dataset and the wind turbine dataset demonstrate the effectiveness and application prospect of the proposed method.

The equilibrium of maritime transport under disaster effects: The case of COVID-19

Ensuring traffic flows remain in equilibrium is crucial in preventing congestion and disruptions in maritime transport chains. Using the fuzzy linear programming method, this article examines how COVID-19 risks have affected the concentration and capacity of maritime cargo flows. The study presents the model, the computational process, and its applications, assessing the transport system's degree of imbalance in 2020-2021 compared to 2018-2019. The model allows for the evaluation of multiple dimensions to obtain an aggregative result. The model provides insights into the dynamics of changes in maritime traffic under the influence of COVID-19. Keywords: Intuitionistic Fuzzy Rough, maritime transport, transport equilibrium, seaborne trade, port calls

Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way

Time-domain astronomy is progressing rapidly with the ongoing and upcoming large-scale photometric sky surveys led by the Vera C. Rubin Observatory project (LSST). Billions of variable sources call for better automatic classification algorithms for light curves. Among them, periodic variable stars are frequently studied. Different categories of periodic variable stars have a high degree of class imbalance and pose a challenge to algorithms including deep learning methods. We design two kinds of architectures of neural networks for the classification of periodic variable stars in the Catalina Survey’s Data Release 2: a multi-input recurrent neural network (RNN) and a compound network combing the RNN and the convolutional neural network (CNN). To deal with class imbalance, we apply Gaussian Process to generate synthetic light curves with artificial uncertainties for data augmentation. For better performance, we organize the augmentation and training process in a “bagging-like” ensemble learning scheme. The experimental results show that the better approach is the compound network combing RNN and CNN, which reaches the best result of 86.2% on the overall balanced accuracy and 0.75 on the macro F1 score. We develop the ensemble augmentation method to solve the data imbalance when classifying variable stars and prove the effectiveness of combining different representations of light curves in a single model. The proposed methods would help build better classification algorithms of periodic time series data for future sky surveys (e.g., LSST).

The impact of financial fair play on the financial performance of Spanish professional football: do the biggest clubs behave better?

PurposeThis study aims to contribute to the analysis of the impact of financial control or “financial fair play” (FFP) regulations on the financial performance of the Spanish professional football league (LaLiga) by examining the moderating role of club size. The authors argue that introducing FFP positively impacted the financial performance of small clubs but increased the economic gap between large and small clubs.Design/methodology/approachA 12-year dataset covering 22 football clubs is used to test the hypotheses. Panel regression models are estimated for eight measures of financial performance indicators, comprising three financial dimensions: profitability, liquidity and solvency. The Gini index is applied to clubs' economic and sports variables to determine the degree of economic imbalance between the largest and smallest clubs.FindingsThe results show that FFP significantly and positively impacted the profitability of small clubs and the solvency of medium-sized clubs but has not impacted the largest clubs' financial performance. After these regulations, economic inequality in Spanish LaLiga increased.Originality/valueThe authors find evidence that club size moderates the effect of FFP on financial performance. The moderating role of club size may explain the mixed results found in previous research. The authors’ findings contribute to improving the literature on the impact of FFP on the financial performance of European football clubs.

A patient with neuropathy and ataxia: what do I have to consider?

An increasing number of peripheral neuro(no)pathies are identified as involving other components of the neurological system, particularly those that further impair balance. Here we aim to outline an evidence-based approach to the diagnosis of patients who present with a somatosensory disorder which also involves at least one other area of neurological impairment such as the vestibular, auditory, or cerebellar systems. Detailed objective investigation of patients who present with sensory impairment, particularly where the degree of imbalance is greater than would be expected, aids the accurate diagnosis of genetic, autoimmune, metabolic, and toxic neurological disease. Diagnosis and management of complex somatosensory disorders benefit from investigation which extends beyond the presenting sensory impairment.

Res-TranBiLSTM: An intelligent approach for intrusion detection in the Internet of Things

The Internet of Things (IoT), as the information carrier of the Internet and telecommunications networks, is a new network technology comprising physical entities embedded with electronic components, software and sensors, and characterized by strong complexity and openness. With the massive amount of data, the occurrence of network intrusion is also increasingly frequent, involving industrial control systems, IoT devices, mobile security, cloud services, and telecommunications services. With the diversification and intelligence of cyberattack behaviors, traditional intrusion detection systems (IDSs) face problems—such as insufficient feature extraction and inaccurate model classification—when faced with high-dimensional features and nonlinear massive data. Due to their powerful data representation learning ability, deep learning methods save substantial time in processing high-dimensional and complex intrusion data. On this basis, we propose an intrusion detection model using ResNet, Transformer and BiLSTM (Res-TranBiLSTM) that takes into account both the spatial and temporal features of network traffic. We use the Synthetic Minor Overriding Technique (SMOTE) – Edited Nearest Neighbor (ENN) method to alleviate the degree of data imbalance. In addition, we respectively establish a spatial feature extraction model based on ResNet and a temporal feature extraction model based on Transformer and BiLSTM to extract spatial features and temporal features parallelly. Finally, spatiotemporal features are included to achieve attack detection and classification. Further, simulation experiments are conducted using the public data sets NSL-KDD and CIC-IDS2017. The experiments are implemented using Python programming language and Pytorch framework. The results reveal that the performance of our proposed model is better than that of other models, with accuracy reaching 90.99%, 99.15% and 99.56%, on NSL-KDD dataset, CIC-IDS2017 dataset and MQTTset dataset, respectively. It increased the detection accuracy by about 1%-10% on NSL-KDD dataset and about 0.2%-10% on CIC-IDS2017 dataset, and about 1%-10% on MQTTset dataset. These results demonstrate that this method is effective in constructing and optimizing large-scale IDS in the IoT environment.

COMPARISON OF DATASET OVERSAMPLING ALGORITHMS AND THEIR APPLICABILITY TO THE CATEGORIZATION PROBLEM

The subject of research in the article is the problem of classification in machine learning in the presence of imbalanced classes in datasets. The purpose of the work is to analyze existing solutions and algorithms for solving the problem of dataset imbalance of different types and different industries and to conduct an experimental comparison of algorithms. The article solves the following tasks: to analyze approaches to solving the problem – preprocessing methods, learning methods, hybrid methods and algorithmic approaches; to define and describe the oversampling algorithms most often used to balance datasets; to select classification algorithms that will serve as a tool for establishing the quality of balancing by checking the applicability of the datasets obtained after oversampling; to determine metrics for assessing the quality of classification for comparison; to conduct experiments according to the proposed methodology. For clarity, we considered datasets with varying degrees of imbalance (the number of instances of the minority class was equal to 15, 30, 45, and 60% of the number of samples of the majority class). The following methods are used: analytical and inductive methods for determining the necessary set of experiments and building hypotheses regarding their results, experimental and graphic methods for obtaining a visual comparative characteristic of the selected algorithms. The following results were obtained: with the help of quality metrics, an experiment was conducted for all algorithms on two different datasets – the Titanic passenger dataset and the dataset for detecting fraudulent transactions in bank accounts. The obtained results indicated the best applicability of SMOTE and SVM SMOTE algorithms, the worst performance of Borderline SMOTE and k-means SMOTE, and at the same time described the results of each algorithm and the potential of their usage. Conclusions: the application of the analytical and experimental method provided a comprehensive comparative description of the existing balancing algorithms. The superiority of oversampling algorithms over undersampling algorithms was proven. The selected algorithms were compared using different classification algorithms. The results were presented using graphs and tables, as well as demonstrated in general using heat maps. Conclusions that were made can be used when choosing the optimal balancing algorithm in the field of machine learning.

Equity and trends in general practitioners’ allocation in China: based on ten years of data from 2012 to 2021

BackgroundGeneral practitioners (GP) are the gatekeepers of residents' health, 2021 is the 10th year of the establishment of the GP system in China. This study aims to assess the equity and trends of GP allocation in China from 2012 to 2021, summarize the efforts and progress of GPs in China during the decade, predict the development trend of GPs in mainland China in the next 5 years to provide a reference for regional health planning and rational allocation of GPs in China.MethodsData from 2012 to 2021 on GPs in 22 provinces, 5 autonomous regions, and 4 municipalities directly under the central government in mainland China (excluding Hong Kong, Macao, and Taiwan) are collected by us. Gini coefficient, Lorenz curve and health resource agglomeration degree (HRAD) were used to analyze the equity of the allocation of GPs in China from different dimensions, a Grey prediction model was used to forecast the number of GPs in 2022–2026.ResultsThe number of GPs in mainland China increased from 109 794 to 434 868 from 2012 to 2021, with 3.08 GPs per 10 000 people in 2021. The Gini coefficient of GPs allocation by population in China decreased from 0.312 to 0.147 from 2012 to 2021, while the Gini coefficient of geographic dimension remained between 0.700 and 0.750. Compared with the degree of curvature of the Lorenz curve in the geographic dimension, the degree of curvature of the population and economic dimension were smaller. In 2021, the HRAD in the Eastern region was 4.618, the Central region was 1.493, with different degrees of imbalance among regions, the HRAD/PAD (population agglomeration degree) in the Eastern, Central and Western regions were 1.196, 0.880 and 0.821, respectively. GPs in the Eastern region is still concentrated, while the Central and Western regions were at a similar level, GPs were more scarce. The GM (1,1) model predicts that the number of GPs in mainland China will reach about 720 000 in 2026, the number of GPs per 10 000 people will reach 4.9.ConclusionAfter a decade of development, the number of GPs in China has increased significantly. It has reached the goal of the GP system when it was first established. However, the equity of the geographical dimension, both in terms of Gini coefficient and HRAD, has great differences between different regions. The average Gini coefficient at the geographic dimension is 0.723. The average HRAD index was 4.969 in the East and 0.293 in the West. The Western region has the problem of insufficient GP allocation in both population and geographical dimension. In the future, the number of GPs in China will continue to grow rapidly with the support of policies. The “2030” goal, proposed in 2018, is expected to be achieved by 2026. Due to certain factors (such as COVID-19), the actual situation may be different from the predicted results.

A novel fault tolerance based load balancing technique in cloud computing

Cloud computing has emerged as one of the most promising technologies for meeting rising computing needs. However, high-performance computing systems are more likely to fail due to the proliferation of components and servers. If a sub-system fails, the entire system may not be functional. In this regard, the occurrence of faults is tolerable using an efficient fault-tolerant method. Since cloud computing involves storing data on a remote network, system failures and congestion are the most common causes of faults. The paper presents a new approach to adopting a fault-tolerant mechanism that adaptively monitors health to detect faults, handles faults using a migration technique, and avoids network congestion. With the advantage of the Ant Colony Optimization (ACO) algorithm and active clustering, the load is distributed evenly in data centers. Simulation results indicate that our algorithm outperforms previous algorithms regarding total execution time and imbalance degree up to 10% and 17%, respectively.

DynaQ: online learning from imbalanced multi-class streams through dynamic sampling

AbstractOnline supervised learning from fast-evolving data streams, particularly in domains such as health, the environment, and manufacturing, is a crucial research area. However, these domains often experience class imbalance, which can skew class distributions. It is essential for online learning algorithms to analyze large datasets in real-time while accurately modeling rare or infrequent classes that may appear in bursts. While methods have been proposed to handle binary class imbalance, there is a lack of attention to multi-class imbalanced settings with varying degrees of imbalance in evolving streams. In this paper, we present the Dynamic Queues (DynaQ) algorithm for online learning in multi-class imbalanced settings to fill this knowledge gap. Our approach utilizes a batch-based resampling method that creates an instance queue for each class to balance the number of instances. We maintain a queue threshold and remove older samples during training. Additionally, we dynamically oversample minority classes based on one of four rate parameters: recall, F1-score, $$\kappa _m$$ κ m , and Euclidean distance. Our learning algorithm consists of an ensemble that uses sliding windows and a soft voting schema while incorporating a drift detection mechanism. Our experimental results demonstrate the superiority of the DynaQ approach over state-of-the-art methods.

Dynamic Offloading Technique for Latency-Sensitive Internet of Things Applications using Fog Computing

Internet of Things (IoT) has evolved as a novel paradigm that provides com-putation power to different entities connected to it. IoT offers services to multiple sectors such as home automation, industrial automation, traffic management, healthcare sector, agriculture industry etc. IoT generally relies on cloud data centers for extended analytics, processing and storage support. The cloud offers highly scalable and robust platform for IoT applications. But latency sensitive IoT applications suffer delay issues as the cloud lies in remote location. Edge/fog computing was introduced to overcome the issues faced by delay-sensitive IoT applications. These platforms lie close to the IoT network, reducing the delay and response time. The fog nodes are usually distributed in nature. The data has to be properly offloaded to available fog nodes using efficient strategies to gain benefit from the integration. Differ-ent offloading schemes are available in the literature to overcome this prob-lem This paper proposes a novel offloading approach by combining two effi-cient metaheuristic algorithms, Honey Badger Algorithm (HBA) and Fla-mingo Search Algorithm (FSA) termed as HB-FS algorithm. The HB-FS is executed in an iterative manner optimizing the objective function in each it-eration. The performance evaluation of the proposed approach is done with different existing metaheuristic algorithms and the evaluations show that the proposed work outperforms the existing algorithms in terms of latency, response time and execution time. The methodology also offers better degree of imbalance with proper load balancing under different conditions.