Task Scheduling in Cloud Computing Environments

Task scheduling in cloud computing involves the allocation and ordering of computing tasks across geographically dispersed, virtualised resources to meet performance, cost and energy objectives. The inherent heterogeneity of hardware, variability in workload arrival and the pay-as-you-go pricing model present a complex optimisation problem. Scheduling algorithms seek to minimise metrics such as makespan, execution cost and energy consumption while respecting Quality of Service requirements like deadlines, throughput and reliability. Approaches range from list-scheduling heuristics to advanced metaheuristic and machine-learning techniques, with growing attention to hybrid and fog-extended cloud architectures. Practical applications include large-scale scientific workflows, real-time Internet of Things data analytics and enterprise business processes. The global proliferation of cloud services has intensified the need for adaptive, scalable and efficient scheduling methods that can respond to dynamic demand, heterogeneous virtual machine configurations and multi-objective trade-offs, ensuring both environmental sustainability and economic viability.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Research from all publishers

Recent studies have explored hybrid metaheuristic strategies and domain-aware enhancements to address the multifaceted challenges of cloud scheduling. A hybrid Particle Whale Optimisation Algorithm (PWOA) has been proposed for workflow scheduling in a cloud–fog environment. By combining global exploration of Whale Optimisation with rapid convergence of Particle Swarm Optimisation, this method minimises total execution time and cost across diverse scientific workflows such as Epigenomics and Montage, demonstrating consistent improvements over standalone heuristics. An Internet-of-Things-based scheduling scheme incorporates deadline and cost constraints by encoding task levels topologically and using a variant of the HEFT heuristic for initial population generation. Novel crossover and mutation operations enhance solution diversity, yielding high success rates in latency-sensitive IoT workflows. Earlier foundational work introduced a hybrid Genetic Algorithm-Particle Swarm Optimisation approach for dependent tasks in cloud environments, achieving significant reductions in makespan and cost while improving load balance across heterogeneous virtual machines. Collectively, these contributions highlight the efficacy of hybrid metaheuristics and level-based task encoding in reconciling competing objectives under dynamic cloud conditions.

Task Scheduling in Cloud Computing Environments publication trend

The graph below shows the total number of articles in task scheduling in cloud computing environments across all publications each year (not limited to Nature Index journals).

Technical terms

Makespan: The total elapsed time to complete a given set of tasks from start to finish.

Workflow scheduling: The process of assigning interdependent tasks, represented as directed acyclic graphs, to computing resources in a specified order.

Metaheuristic algorithm: An optimisation method combining multiple search strategies to efficiently explore large and complex solution spaces.

Fog computing: A decentralised computing layer that extends cloud services to the network edge, reducing latency for time-sensitive tasks.

Hybrid cloud: An infrastructure combining private and public cloud resources to balance control, scalability and cost.

Quality of Service (QoS): A set of performance metrics, such as deadline adherence and reliability, that scheduling solutions must satisfy.

References

1. A Hybrid Particle Whale Optimization Algorithm with application to workflow scheduling in cloud–fog environment. Decision Analytics Journal (2023).
2. An IoT-based task scheduling optimization scheme considering the deadline and cost-aware scientific workflow for cloud computing. EURASIP Journal on Wireless Communications and Networking (2019).
3. Workflow Scheduling Using Hybrid GA‐PSO Algorithm in Cloud Computing. Wireless Communications and Mobile Computing (2018).