Task scheduling in complex, heterogeneous fog–cloud computing environments remains a challenging NP-hard optimization problem. Balancing conflicting objectives such as makespan, energy consumption, and processing costs becomes increasingly difficult as system workloads expand. A recent study published in the Journal of Cloud Computing introduces an Enhanced Lemurs Optimizer (ELO) designed to improve efficiency in these multi-objective scheduling scenarios.
The research team developed the ELO to address limitations observed in existing metaheuristics, which often suffer from premature convergence due to suboptimal initialization or inflexible exploration-exploitation dynamics. By seeding the standard Lemurs Optimizer with a problem-aware heuristic schedule under a weighted-sum scalarization framework, the researchers created a method that more effectively navigates the complex search space of fog-cloud architectures.
For larger workloads of 200 to 400 tasks, the ELO demonstrated significant performance gains. It achieved higher weighted fitness scores, improving on the original Lemurs Optimizer by 15.9 to 19.6 percent. Furthermore, the framework reduced makespan and energy consumption by up to 24.2 percent and 21.8 percent, respectively.
The study’s results indicate that the ELO’s performance advantage grows as the task size increases. For smaller workloads of 100 tasks, however, the researchers noted that simulated annealing remained marginally superior, with a 0.5 percent higher mean fitness.
An ablation study conducted by the researchers revealed that the heuristic initialization is the primary driver behind the framework’s improved efficiency. These findings establish the Enhanced Lemurs Optimizer as a robust framework for weighted-sum scheduling in heterogeneous computing environments.
The researchers evaluated the optimization framework using thirty paired runs on shared computing instances, ensuring an equal evaluation budget across all tested metaheuristics. Statistical verification through paired Wilcoxon signed-rank tests confirmed the performance advantages observed across different task sizes.
Subject of Research: Optimization of multi-objective task scheduling in fog-cloud computing architectures
Article Title: Enhanced lemurs optimizer for multi-objective task scheduling in heterogeneous fog–cloud architectures
Article References: Ababneh, N., Kamal Abasi, A., Hamid, Y., & Koci, A. (2026). Enhanced lemurs optimizer for multi-objective task scheduling in heterogeneous fog–cloud architectures. Journal of Cloud Computing. https://doi.org/10.1186/s13677-026-01018-w
Image Credits: AI Generated
DOI: 10.1186/s13677-026-01018-w
Keywords: Fog Computing, Cloud Computing, Task Scheduling, Metaheuristics, Lemurs Optimizer, Multi-objective Optimization, Energy Consumption, Makespan Minimization, NP-hard Problems, Heuristic Initialization, Weighted-sum Scalarization, Computational Efficiency, Heterogeneous Architectures, Algorithm Performance, Wilcoxon Signed-rank Test
Cite Scienmag News
Denise Maddox. (November 16, 2026). Enhanced Lemurs Optimizer Boosts Task Scheduling Efficiency in Fog-Cloud Systems. Scienmag. https://scienmag.com/enhanced-lemurs-optimizer-boosts-task-scheduling-efficiency-in-fog-cloud-systems/
Denise Maddox. "Enhanced Lemurs Optimizer Boosts Task Scheduling Efficiency in Fog-Cloud Systems." Scienmag, 16 November 2026, https://scienmag.com/enhanced-lemurs-optimizer-boosts-task-scheduling-efficiency-in-fog-cloud-systems/. Accessed 16 November 2026.
Denise Maddox. "Enhanced Lemurs Optimizer Boosts Task Scheduling Efficiency in Fog-Cloud Systems." Scienmag. November 16, 2026. https://scienmag.com/enhanced-lemurs-optimizer-boosts-task-scheduling-efficiency-in-fog-cloud-systems/








