Jul 2026· IEEE International Conference on Engineering of Complex Computer Systems· pp. 1-7· 0 citations· 13 references
Abstract
Energy-aware task scheduling in heterogeneous cloud infrastructures remains challenging due to the combinatorial growth of task-to-resource assignments, resource heterogeneity, and the need to balance energy consumption with scheduling performance. This paper proposes an Adaptive Dominance-Guided Grey Wolf Optimizer (ADG-GWO) for non-preemptive task scheduling in heterogeneous cloud environments. ADG-GWO adapts Grey Wolf Optimization to discrete task-to-VM assignment by integrating dominance-guided genetic reproduction, Hamming-distance-based diversity regulation, and adaptive reproduction control. These mechanisms are designed to improve search stability, reduce premature convergence, and support effective exploration of high-dimensional assignment spaces without expanding the externally tuned hyperparameter space.The proposed method is evaluated through simulation under workload-scaling and capacity-scaling scenarios using heterogeneous cloud configurations. For evaluation, workload instances and heterogeneous VM configurations are derived from Google Cluster Trace 2019 to instantiate realistic task-to-VM scheduling scenarios. The results show that the proposed dominance-guided adaptive search improves energy-aware scheduling effectiveness while maintaining competitive scheduling efficiency in heterogeneous cloud environments.
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.
M. Yacoub, Ahmed E. Abdel Raouf, Walaa K. Gad et al.· Electronics· 0 citations
A Risk-Aware Task Scheduling Strategy (RATSS) that incorporates variability into the optimization process by minimizing the standard deviation of makespan and waiting time, thereby reducing execution uncertainty and demonstrating improved stability, fairness, and overall system performance.
Nisha Saini, J. Kumar· Malaysian Journal of Compute...· 0 citations
Experimental results demonstrate that DL-EATS achieves the lowest energy consumption, shortest makespan, minimal SLA violation rate, and highest resource utilization, representing an 18.5% improvement in energy efficiency over the next best method and substantial gains across all performance metrics.
Abdulmumini Adamu, A. A. Abdulwasiu· Journal of Science Research...· 0 citations
Efficient energy scheduling in heterogeneous computing environments is a critical challenge, as task allocation decisions directly affect both energy consumption and execution performance. This work presents an energy aware scheduling framework based on a discretized grasshopper optimization algorithm (GOA), designed to balance energy reduction with acceptable makespan. The model formulates scheduling as a constrained objectives optimization problem, incorporating energy use, makespan, heterogeneous resource capacities, workflow precedence, and non preemptive execution. A constant aware representation and repair based decoding strategy enable GOA to generate feasible task to resources assignments. Implemented in Python, the framework is evaluated against HEFT, Min and Random scheduling under varying workload. Results show that the schedules based on GOA achieves lower energy consumption and improved performance delay energy while maintaining competitive makespan, with performance gains becoming more pronounced as workload complexity increases. These findings demonstrate the scalability and effectiveness of discretised GOA as a metaheuristic solution for energy aware scheduling in heterogeneous systems.
Macauley Opuwari, C. Igiri, D. Ikeh· International Journal Of Eng...· 0 citations
A lightweight Greedy Predictive Scheduling (GPS) algorithm that combines predictive resource utilization estimation with greedy host selection to improve scheduling decisions across heterogeneous multi-region cloud environments is proposed.
M. Yacoub, Ahmed E. Abdel Raouf, Walaa K. Gad et al.· Future Internet· 0 citations
Resource allocation in the cloud-edges is extremely important to reduce the time of execution, energy usage, and service-level agreement (SLA) breaches when experiencing dynamic workloads. In this paper, the author has proposed an elite co-evolution hybrid optimization model, Hybrid Hierarchical Optimization for Cloud Allocation (H2O-Cloud), which combines Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) using periodic elite migration and adaptive multi-objective evaluation. The suggested approach is also optimal in terms of makespan, SLA violation rate, energy consumption, and resource usage. Real world Azure LLM Inference Trace datasets (both code-generation, conversational AI) were used to run experiments. The analysis took into account scalable loads of 300 to 1200 tasks on heterogeneous cloud virtual machines, edge-only and hybrid edge-cloud infrastructure. Measurements confirm that H2O-Cloud is drastically more efficient than traditional FCFS scheduling with the maximum makespan decrease of 39.7% and throughput enhancement of 65.8% and SLA violation decrease of 17.1% when using the cloud only (900-task workload). The proposed approach results in an 8.0 percent reduction in makespan and a better resource utilization than PSO. Moreover, H2O-Cloud remains competitive in terms of energy efficiency and also shows better scalability to a larger amount of tasks. The strength of the proposed approach is statistically verified with the help of paired tests. This hybrid co-evolution mechanism contributes to both global exploration and local refinement at the same time, which allows the stable convergence and best load balancing on heterogeneous resources. The framework also exhibits high flexibility in edge-cloud hybrid systems, which minimizes SLA breaches and balances the energy usage. The experimental results confirm H2O-Cloud as a strong, scalable and SLA conscious resource provision strategy to next-generation AI-driven cloud computing systems.
D.Bhuvaneswari, S.Jeevitha, Prashant Sangulagi et al.· 2026 6th International Confe...· 0 citations