Masterpiece Optimization Algorithm-Based Priority-Aware Load Balancing Strategy for Cloud Data Centers

SPES: A Stochastic Predictive Energy-Aware Scheduling Approach for Efficient Multi-Region Cloud Computing

Cloud computing has transformed the delivery of modern applications and services by providing scalable, flexible, and cost-effective access to computing resources. One of the most critical challenges in cloud environments is the efficient distribution of dynamic workloads across heterogeneous resources, commonly addressed through load balancing and task scheduling techniques. Efficient scheduling plays a vital role in maximizing resource utilization, minimizing response time, and maintaining acceptable Quality of Service (QoS), particularly under dynamic and large-scale workloads. Despite the progress achieved by traditional heuristics such as Min-Min and metaheuristic approaches like the Improved Sparrow Search Algorithm (ISSA), challenges related to scalability, adaptability, and computational overhead remain. Metaheuristic-based approaches often involve iterative optimization processes that may limit their efficiency in real-time scheduling scenarios. In this paper, we propose a lightweight Stochastic Predictive Energy-Aware Scheduling (SPES) algorithm that integrates predictive execution estimation, multi-resource awareness, and stochastic decision-making. Unlike deterministic scheduling strategies, SPES employs a Top K candidate selection mechanism combined with probabilistic weighting and epsilon-greedy exploration to enhance adaptability and avoid suboptimal resource allocation. The proposed method considers CPU, memory, and I/O demands to achieve balanced utilization across heterogeneous hosts while implicitly addressing energy efficiency through utilization-based modeling. The proposed algorithm is implemented and evaluated using the CloudSim 5.0 simulation framework under heterogeneous multi-region cloud environments with varying workload sizes. Experimental results demonstrate that SPES consistently outperforms ISSA and achieves makespan reductions of up to 23.8% while improving scalability, resource utilization, and scheduling efficiency under dynamic cloud workloads. These results indicate that SPES provides an effective lightweight scheduling solution for large-scale and energy-aware cloud computing environments and supports green computing objectives through improved resource efficiency.

A Hybrid Framework for Joint Optimization of Resource Allocation and Load Balancing in Cloud Systems

Experiments show that the proposed Hybrid Framework for Joint Optimization of Resource Allocation and Load Balancing that spans two layers in heterogeneous cloud computing systems obtains 25-30% energy savings compared with ordinary methods, significantly reduces p95 latency and also achieves a relatively better Quality Of Service.

Scalable Load Balancing Algorithms for Cloud Infrastructures

Cloud computing has become a paradigm of providing dynamically scalable and on-demand computing in the Internet. Effective load balancing is one of the most significant issues in cloud environment that guarantees optimal resource use, low response time, high availability, and quality of service (QoS). Traditional methods of load balancing are inadequate as cloud infrastructures increase due to scale and complexity because of the dynamism and heterogeneity in their workloads. As a result, there is a need to have scalable and flexible load balancing strategies that would efficiently distribute workloads in large-scale cloud data centres. The paper provides a detailed research of the scalable load-balancing algorithms to the cloud infrastructures in terms of their architectural principles, performance indicators, scaling attributes, and fault-tolerance. Some of the classical and state of the artload balancing algorithms, such as, are statical, dynamic, heuristic, and nature inspired strategies that are reviewed in the paper. It is also suggested that a new approach to scaling hybrid load balancing methodology should be offered because it combines distributed decision-making with predictive estimation of workload. The suggested solution is intended to increase the throughput of the system, reduce the response time, and optimize the use of resources in the presence of highly changing workloads. A long analysis assessment and comparative report is carried out to reveal the efficiency of the scalable load balancing strategies at the large-scale cloud environment. The findings show that adaptive algorithm and hybrid algorithm is better in scalability, robustness and the overall performance of the system compared to the traditional centralized algorithms. The results of this paper can be helpful to researchers and practitioners during the development of the next-generation cloud load balancing mechanisms.

Efficient Load Balancing Using Enhanced Dragonfly with Firefly Optimization Over Cloud Computing Environment

The large number of users of the cloud has resulted in a rapid increase in the number of requests for tasks, and scheduling tasks efficiently and load balancing them across non-homogeneous virtual machines (VMs) has become an urgent matter. This is a problem that is inherently NP-hard, especially when the Objective is to optimize multiple Objectives, such as makespan, execution cost, scheduling time, and resource utilization. Current meta-heuristic methods, such as the Particle Swarm Optimization (PSO), are computationally expensive and do not converge to global optimality when applied in isolation. To overcome these shortcomings, this paper proposes an Enhanced Dragonfly-Firefly Optimization (EDFO) algorithm, coupled with an Improved Advanced Encryption Standard (IAES) mechanism for safe and effective scheduling of cloud tasks. The EDFO model was an effort to merge the global search capability of the Dragonfly algorithm and the local refinement strength of the Firefly algorithm. The multi-objective function is formulated to minimize the maximum difference in VM completion times and to achieve even workloads. The results of the proposed EDFO-IAES are experimentally evaluated and shown to be much more effective than currently used methods such as DFGA and IBPSO-LBS. In particular, the imbalance level decreases to 0.45, the average storage usage increases to about 94%, and makepan is minimized by nearly a quarter across the workload variabilities. Besides, incorporating IAES increases data security without imposing a substantial computational burden. All in all, the suggested framework is more efficient, scalable, and secure, which is why it can be considered a viable solution for a real-life cloud computing setup.

Energy-Efficient Hybrid Metaheuristic Resource Allocation Model for Dynamic Virtual Machine Scheduling in Cloud Computing Platforms

An Efficient Task Scheduling Approach in Cloud Computing Using Hybrid Fruit Fly and Ant Colony Optimization Techniques

Although cloud computing offers on-demand resources, effective job scheduling is still a major challenge to increase efficiency and resource usage. For large-scale, dynamic workloads, traditional algorithms s FCFS and Min-Min are straightforward yet ineffective. In order to generate high-quality task–VM mappings, this study suggests a hybrid nature-inspired algorithm called fruit fly optimization–ant colony optimization (FOA-ACO), which combines the exploitative ant colony optimization (ACO) and the exploratory fruit fly optimization algorithm (FOA). Minimizing makespan, optimizing resource usage, and distributing load evenly among virtual machines (VM) are the objectives. Workload traces from PlanetLab and CloudSim 3.0.3 are used to assess the method in a variety of experimental scenarios involving up to 1000 jobs and numerous diverse VM. The suggested FOA-ACO methodology enhances overall cloud performance by decreasing the makespan by 9.57%, employing more resources by 7.14%, and enhancing the load balancing factor (LBF) by 23.06%. This was observed by comparing it with other approaches such as FCFS, Min-Min, solo ACO, and WOA. An effective solution to the scheduling problems in today’s cloud environments is provided by this hybrid method. Future research may concentrate on refining the system to take into consideration various objectives, such as cost and reliability, enhancing its use of energy, and optimizing its performance with very massive cloud setups. Also, the approach might be refined to facilitate decision-making in real time and incorporate machine learning methods for greater flexibility.